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

    Neuronpedia

    INDEX
    Explanations

    words related to movement from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating movement or transitions from one place or state to another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     secondly
    -0.78
     exceptions
    -0.76
    wcsstore
    -0.75
    allowed
    -0.68
     deviations
    -0.66
    ioned
    -0.65
    Ry
    -0.64
    tek
    -0.63
    Animation
    -0.62
    Attempts
    -0.61
    POSITIVE LOGITS
    pless
    0.86
    ggles
    0.79
    schild
    0.78
    umbn
    0.74
     prominence
    0.72
    oter
    0.70
    psy
    0.69
     Eternity
    0.68
    ilet
    0.68
    cair
    0.68
    Act Density 0.077%

    No Known Activations