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

    Neuronpedia

    INDEX
    Explanations

    words related to various forms of rescue and rescinding actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rescue operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drive
    -0.72
    ception
    -0.71
     Idea
    -0.68
    ahi
    -0.68
    Drive
    -0.66
     Spice
    -0.65
     MAD
    -0.65
    vine
    -0.64
    CHAT
    -0.62
    ophone
    -0.62
    POSITIVE LOGITS
     resc
    4.22
     rescind
    1.42
     kidn
    1.08
     disapp
    1.04
     scaling
    0.99
     retri
    0.99
     unsc
    0.96
     presc
    0.95
     rescuing
    0.94
     recomm
    0.94
    Act Density 0.032%

    No Known Activations