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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to function declaration and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.84
     beginnetje
    -0.84
    featureID
    -0.80
     autorytatywna
    -0.80
    ьаж
    -0.78
     Infórmanos
    -0.76
     tartalomajánló
    -0.75
     صوتيه
    -0.73
    Tikang
    -0.71
     nahilalakip
    -0.70
    POSITIVE LOGITS
     etc
    0.60
    ↵↵↵
    0.45
    etc
    0.45
    以及
    0.41
    Additionally
    0.40
     Additionally
    0.39
     and
    0.39
    ↵↵↵↵
    0.39
    ↵↵
    0.39
     moreover
    0.38
    Act Density 0.869%

    No Known Activations