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

    Neuronpedia

    INDEX
    Explanations

    instances where someone forgets something

    oai_token-act-pair · gpt-3.5-turbo

    instances of forgetting or misplacing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amen
    -0.81
    uterte
    -0.73
    Parser
    -0.73
    osion
    -0.70
    Builder
    -0.67
    berus
    -0.65
    ourke
    -0.65
    ä½ľ
    -0.65
    elled
    -0.64
    XY
    -0.64
    POSITIVE LOGITS
    fulness
    1.14
    fully
    0.96
     about
    0.88
    ful
    0.88
    table
    0.87
     ABOUT
    0.81
     how
    0.73
    ingly
    0.71
     About
    0.71
     inconvenient
    0.71
    Act Density 0.034%

    No Known Activations