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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating worthiness or deservingness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of worthiness or merit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullivan
    -0.81
    glers
    -0.75
    nels
    -0.69
     interstate
    -0.67
    lems
    -0.67
    ories
    -0.66
     synchronized
    -0.64
     processes
    -0.62
     surfing
    -0.61
     recruited
    -0.61
    POSITIVE LOGITS
     praise
    0.88
    cellence
    0.78
     scorn
    0.77
     criticism
    0.75
    EDIT
    0.75
    cipled
    0.74
     ridicule
    0.70
    ãģĭ
    0.70
     accol
    0.70
    inguished
    0.70
    Act Density 0.102%

    No Known Activations