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

    Neuronpedia

    INDEX
    Explanations

    instances of reports or reporting of various events and incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.80
    ortium
    -0.78
     ILCS
    -0.73
    phabet
    -0.72
    osate
    -0.71
    atron
    -0.69
    arton
    -0.69
    err
    -0.67
    schild
    -0.67
    wrap
    -0.66
    POSITIVE LOGITS
     seeing
    1.35
     receiving
    1.32
     experiencing
    1.30
     encountering
    1.25
     feeling
    1.20
     having
    1.16
     finding
    1.16
     witnessing
    1.14
     noticing
    1.14
     smelling
    1.07
    Act Density 0.079%

    No Known Activations