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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or official procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of events or actions that involve opening, particularly in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jad
    -0.73
    kh
    -0.71
    ansk
    -0.66
    typ
    -0.65
     Krish
    -0.65
    cdn
    -0.65
    kov
    -0.65
    chem
    -0.65
    zik
    -0.63
    bot
    -0.63
    POSITIVE LOGITS
     doors
    0.87
     backdoor
    0.82
     door
    0.80
     Pandora
    0.80
    izons
    0.76
    uberty
    0.74
     airspace
    0.73
     Entry
    0.73
     hatch
    0.69
     Doors
    0.67
    Act Density 0.131%

    No Known Activations