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

    Neuronpedia

    INDEX
    Explanations

    words related to negative emotions or situations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouver
    -0.80
     pegged
    -0.70
    authorized
    -0.69
    vernment
    -0.67
    rity
    -0.64
     sterling
    -0.64
    aeda
    -0.64
     irrig
    -0.63
     nomine
    -0.63
    lav
    -0.62
    POSITIVE LOGITS
    omas
    1.38
    istic
    1.33
    istically
    1.33
    der
    1.19
    istical
    1.01
    omic
    0.90
    onna
    0.86
    hus
    0.84
    stal
    0.83
    die
    0.82
    Act Density 0.072%

    No Known Activations