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

    Neuronpedia

    INDEX
    Explanations

    verbs related to legal or procedural actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cancellation, appeal, and refunding actions in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.73
    zbollah
    -0.62
    ashington
    -0.61
    FORE
    -0.58
    erala
    -0.57
    industrial
    -0.57
     Thou
    -0.56
    itched
    -0.55
    itcher
    -0.54
     guiActiveUnfocused
    -0.54
    POSITIVE LOGITS
     them
    1.15
    uate
    1.10
     yourself
    1.08
     oneself
    1.08
     anything
    0.97
     everything
    0.94
     him
    0.91
     accordingly
    0.91
     your
    0.91
     yourselves
    0.90
    Act Density 0.535%

    No Known Activations