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

    Neuronpedia

    INDEX
    Explanations

    headings, section titles, and navigation elements related to website content and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InstanceState
    -0.55
     (
    -0.51
    tagHelperRunner
    -0.50
    tojas
    -0.48
     tot
    -0.47
    Kjelder
    -0.46
     be
    -0.45
     ProtoMessage
    -0.45
    ainya
    -0.44
    oneofs
    -0.44
    POSITIVE LOGITS
     itſelf
    0.80
     myſelf
    0.78
     himſelf
    0.72
     Efq
    0.71
     iſt
    0.70
     themſelves
    0.68
     postulates
    0.67
    spesies
    0.67
     doubtnut
    0.66
    ſelf
    0.65
    Act Density 0.450%

    No Known Activations