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

    Neuronpedia

    INDEX
    Explanations

    expressions of subjective experience and personal opinion

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

    best we can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.70
     avoient
    -0.60
    GEBURTSDATUM
    -0.57
     ſtate
    -0.56
     houſe
    -0.54
     Houſe
    -0.53
    MLLoader
    -0.52
     étoient
    -0.50
     ſame
    -0.50
     سكانية
    -0.50
    POSITIVE LOGITS
    :✨
    0.52
     Besten
    0.47
    others
    0.46
    Others
    0.42
     others
    0.42
     BEST
    0.41
     Best
    0.41
     Others
    0.41
    best
    0.40
     best
    0.40
    Act Density 0.034%

    No Known Activations