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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty and indications of conditions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.74
     raiſ
    -0.73
     itſelf
    -0.73
     Eſ
    -0.73
     Diſ
    -0.73
     ſeveral
    -0.72
     pleaſure
    -0.71
     ſmall
    -0.69
     Monfieur
    -0.69
     myſelf
    -0.68
    POSITIVE LOGITS
     setuptools
    0.57
    <>(
    0.49
     indicate
    0.48
    indic
    0.47
     serious
    0.46
     a
    0.44
     indicating
    0.44
     Serious
    0.43
     approach
    0.43
    SequentialGroup
    0.43
    Act Density 0.356%

    No Known Activations