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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating research results or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angu
    -0.56
     Alf
    -0.55
    AutoScaleMode
    -0.55
     المعيارى
    -0.52
     Mange
    -0.51
    픈
    -0.50
    Care
    -0.50
     else
    -0.49
     ethics
    -0.49
     хто
    -0.49
    POSITIVE LOGITS
     ejus
    0.76
    PMID
    0.71
     zitate
    0.68
     AspNetCore
    0.65
     zijne
    0.63
    ragamo
    0.63
     مشين
    0.63
    PostExecute
    0.62
    Viitteet
    0.62
    izr
    0.61
    Act Density 0.497%

    No Known Activations