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

    Neuronpedia

    INDEX
    Explanations

    instances where a suggestion or alternative course of action is presented

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fla
    -0.81
    ĸļ
    -0.73
    icing
    -0.67
    Raven
    -0.66
    htaking
    -0.63
     Naz
    -0.60
    Hol
    -0.59
    ãĤ£
    -0.58
    hess
    -0.58
    iami
    -0.58
    POSITIVE LOGITS
     goto
    0.89
     nevertheless
    0.83
     forfeit
    0.78
    throw
    0.76
     simply
    0.74
     blame
    0.73
     revert
    0.73
     recourse
    0.72
     alternatively
    0.70
     despair
    0.68
    Act Density 0.301%

    No Known Activations