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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the existence or accessibility of information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     curfew
    -0.73
    venge
    -0.73
     lifelong
    -0.65
     ditch
    -0.62
     celebrates
    -0.60
    ocent
    -0.60
     salute
    -0.59
     conscious
    -0.58
     standby
    -0.58
     chant
    -0.58
    POSITIVE LOGITS
     HERE
    1.30
     below
    1.21
     Below
    1.10
     BELOW
    1.09
     Appendix
    1.08
    Below
    1.07
    PDF
    1.05
    pdf
    1.03
     here
    1.03
     pdf
    0.99
    Act Density 0.165%

    No Known Activations