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

    Neuronpedia

    INDEX
    Explanations

    responses or reactions to various situations or statements

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions, challenges, and various forms of expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     notor
    -0.81
     Palestin
    -0.78
     Leban
    -0.71
     reluct
    -0.71
     withd
    -0.68
    VIDIA
    -0.68
     destro
    -0.68
    avascript
    -0.66
     millenn
    -0.64
    ailability
    -0.62
    POSITIVE LOGITS
    ings
    1.29
    able
    1.23
    ingly
    1.14
    ables
    1.05
    backs
    0.98
    ments
    0.95
    ably
    0.95
    ability
    0.92
    downs
    0.89
    INGS
    0.89
    Act Density 0.735%

    No Known Activations