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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussing various topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of discussions or mentions of various topics and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kie
    -0.81
    OGR
    -0.71
    arton
    -0.71
    cue
    -0.69
    Original
    -0.69
    erenn
    -0.68
    ologue
    -0.68
    ezvous
    -0.67
    vt
    -0.66
    quer
    -0.65
    POSITIVE LOGITS
     how
    1.39
     wanting
    1.20
     needing
    1.16
     why
    1.00
     improving
    0.93
     overcoming
    0.93
     virtues
    0.91
     reforming
    0.90
     hating
    0.89
     impending
    0.89
    Act Density 0.173%

    No Known Activations