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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters or official procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental authority and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rama
    -0.74
    okes
    -0.74
    mallow
    -0.70
    vp
    -0.69
    ecided
    -0.66
    agame
    -0.66
    wolves
    -0.65
    arians
    -0.63
    dress
    -0.63
     Countdown
    -0.63
    POSITIVE LOGITS
     complicity
    1.15
     behest
    1.12
     encouragement
    1.12
     ausp
    1.08
     assumption
    1.08
     sole
    1.03
     assistance
    1.01
     conn
    0.99
     consent
    0.98
     expectation
    0.97
    Act Density 0.288%

    No Known Activations