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

    Neuronpedia

    INDEX
    Explanations

    mentions of relationships or interactions with peers or colleagues

    oai_token-act-pair · gpt-3.5-turbo

    references to companionship or partnerships, especially in the context of "mates."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.81
    atra
    -0.78
    icer
    -0.75
    icum
    -0.74
    immer
    -0.74
    aceous
    -0.72
    older
    -0.71
    acco
    -0.71
    SIGN
    -0.69
    ooks
    -0.69
    POSITIVE LOGITS
    mates
    1.09
    mate
    0.97
     Roc
    0.84
     Swap
    0.75
     Eps
    0.73
     pupils
    0.68
     Delete
    0.68
     Sylvia
    0.68
     Goo
    0.67
     Polly
    0.66
    Act Density 0.009%

    No Known Activations