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

    Neuronpedia

    INDEX
    Explanations

    references to specific events, actions, or statements in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.69
     houſe
    -0.68
     CWE
    -0.65
     Chriftian
    -0.63
     Houſe
    -0.62
     itſelf
    -0.61
    DMETHOD
    -0.60
    ſelf
    -0.60
     ſche
    -0.60
     purpoſe
    -0.60
    POSITIVE LOGITS
     went
    0.56
     immediately
    0.56
     let
    0.52
     promptly
    0.52
    不去
    0.51
     go
    0.51
     imme
    0.49
     proceeded
    0.49
    そのまま
    0.47
     Ignore
    0.47
    Act Density 0.409%

    No Known Activations