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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey significant actions or changes

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

    Word "and" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    actions or events after conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    -0.81
     также
    -0.76
    égal
    -0.72
     همچنین
    -0.71
    also
    -0.68
     alfo
    -0.68
     Also
    -0.68
     linkovi
    -0.68
     juga
    -0.67
    Also
    -0.67
    POSITIVE LOGITS
     when
    0.88
     everything
    0.81
     they
    0.81
     everyone
    0.76
     within
    0.73
     we
    0.72
     everybody
    0.72
    everything
    0.71
     когато
    0.71
     after
    0.69
    Act Density 0.231%

    No Known Activations