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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time and specific temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achs
    -0.17
    orno
    -0.17
    лоп
    -0.17
    rike
    -0.16
    ص
    -0.15
    witter
    -0.15
    aly
    -0.14
    lish
    -0.14
    rite
    -0.14
     Herz
    -0.14
    POSITIVE LOGITS
     weekends
    0.30
     source
    0.19
     Weekend
    0.19
     weekend
    0.17
     pains
    0.15
    erdem
    0.15
    æľ
    0.15
     Source
    0.15
    /*****************************************************************************↵
    0.15
    ROL
    0.14
    Act Density 0.073%

    No Known Activations