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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the source or origin of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the source or origin of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umption
    -0.75
    merce
    -0.74
    fps
    -0.73
    uploads
    -0.72
    knife
    -0.71
    idav
    -0.71
    currency
    -0.71
    cas
    -0.70
    soon
    -0.70
    perty
    -0.69
    POSITIVE LOGITS
     afar
    1.02
     nowhere
    0.95
     somewhere
    0.92
     whence
    0.91
     scratch
    0.85
     abroad
    0.79
     obscurity
    0.77
     behind
    0.75
     inside
    0.73
     elsewhere
    0.73
    Act Density 0.063%

    No Known Activations