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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or reactions by people

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to social dynamics or commentary on societal behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obbies
    -0.57
    nown
    -0.56
    £ı
    -0.55
    Interstitial
    -0.54
    ļéĨĴ
    -0.53
     teasp
    -0.53
    orld
    -0.53
    entimes
    -0.53
    erential
    -0.52
     nurt
    -0.52
    POSITIVE LOGITS
     this
    1.05
     these
    0.95
     Tsarnaev
    0.80
     THIS
    0.74
     Canaver
    0.72
    these
    0.70
     SCP
    0.69
    this
    0.68
     THESE
    0.68
     Melania
    0.68
    Act Density 1.049%

    No Known Activations