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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moving or progressing forward in some way

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "go"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ament
    -0.69
    ificent
    -0.68
    creen
    -0.63
    itionally
    -0.61
    eers
    -0.60
     Horus
    -0.59
     anomalies
    -0.58
    ifully
    -0.58
     Disaster
    -0.57
    icio
    -0.57
    POSITIVE LOGITS
    vt
    1.09
    ggle
    1.09
    verning
    1.08
    lems
    1.06
    ALK
    0.91
     overboard
    0.88
     ahead
    0.81
     forth
    0.81
    aded
    0.79
    ogly
    0.79
    Act Density 0.077%

    No Known Activations