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

    Neuronpedia

    INDEX
    Explanations

    references to time-related phrases or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACT
    -0.15
    kening
    -0.14
    eriod
    -0.14
    ë¦Ħ
    -0.14
    aras
    -0.14
    ieber
    -0.14
    &type
    -0.14
     Morm
    -0.14
    zim
    -0.14
    cheng
    -0.14
    POSITIVE LOGITS
    199
    0.19
    198
    0.18
     childhood
    0.17
    197
    0.16
    IFI
    0.16
    aje
    0.15
    akk
    0.15
    196
    0.14
     Bol
    0.14
    201
    0.14
    Act Density 0.043%

    No Known Activations