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

    Neuronpedia

    INDEX
    Explanations

    references to guidance and assistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.77
    UnsafeEnabled
    -0.75
     itſelf
    -0.71
    WebVitals
    -0.70
     Cæsar
    -0.67
     OnInit
    -0.63
     Anſ
    -0.61
     Efq
    -0.60
    ναι
    -0.59
     Monfieur
    -0.59
    POSITIVE LOGITS
     nélkül
    0.60
     EdgeInsets
    0.57
    posedge
    0.52
    Ohne
    0.50
    govine
    0.48
    CrossRef
    0.47
    وفق
    0.46
    aarrggbb
    0.45
    SpringRunner
    0.45
     jadx
    0.45
    Act Density 0.494%

    No Known Activations