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

    Neuronpedia

    INDEX
    Explanations

    words related to positive experiences or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    words associated with positive experiences or feelings of refreshment and reward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iatrics
    -0.78
    efer
    -0.76
    ariat
    -0.74
    riage
    -0.70
    OPE
    -0.69
    talk
    -0.69
    deal
    -0.69
    ellect
    -0.68
    peria
    -0.68
    behind
    -0.67
    POSITIVE LOGITS
    ly
    1.09
    tons
    0.97
    LY
    0.91
    theless
    0.79
    NESS
    0.77
     conduc
    0.75
     atmosp
    0.73
     heights
    0.71
     corrid
    0.71
     qualities
    0.71
    Act Density 0.082%

    No Known Activations