Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to data usage and targeting in marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    uncertainty or indirect information

    np_acts-logits-general · gemini-2.0-flash

    words suggesting supposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maravilh
    -0.82
     wspania
    -0.82
     wonderful
    -0.81
     veramente
    -0.76
     our
    -0.75
     nossas
    -0.75
     magnificent
    -0.74
     marvelous
    -0.74
     великолеп
    -0.73
     maravillosa
    -0.73
    POSITIVE LOGITS
     reportedly
    1.16
     unspecified
    1.01
     apparently
    0.95
     allegedly
    0.93
     Apparently
    0.91
     supposedly
    0.90
    apparently
    0.88
    Apparently
    0.88
    supposed
    0.83
     purported
    0.79
    Act Density 0.232%

    No Known Activations