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

    Neuronpedia

    INDEX
    Explanations

    the letter "t" in sentences ending with different expressions and contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "wouldn't" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     medium
    -0.58
     linkage
    -0.57
     assessments
    -0.57
     Balkans
    -0.57
    Kings
    -0.56
     modem
    -0.56
     Alleg
    -0.54
     Medium
    -0.54
    åĬ
    -0.53
     comparisons
    -0.53
    POSITIVE LOGITS
     necessarily
    1.00
    urtle
    0.96
     hesitate
    0.90
    ournament
    0.83
    apest
    0.83
     hesitated
    0.82
    aper
    0.80
    aylor
    0.79
     bud
    0.77
     interfere
    0.77
    Act Density 0.025%

    No Known Activations