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

    Neuronpedia

    INDEX
    Explanations

    actions related to possession or retention

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "keep."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ode
    -0.80
    NESS
    -0.79
    atana
    -0.74
    ooter
    -0.71
    inals
    -0.68
    iliary
    -0.67
    assi
    -0.67
    sonian
    -0.66
    uably
    -0.65
    KY
    -0.63
    POSITIVE LOGITS
     tabs
    1.27
     track
    1.09
     secrets
    1.02
     afloat
    0.98
     pace
    0.97
     vigil
    0.96
     quiet
    0.95
     secret
    0.92
     kosher
    0.87
     meticulous
    0.84
    Act Density 0.050%

    No Known Activations