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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and statements expressing potential actions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \\
    -0.54
     (
    -0.51
    ↵
    -0.50
    …
    -0.48
    ...
    -0.47
    ↵↵
    -0.47
     I
    -0.47
     A
    -0.46
     $\
    -0.45
     .
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    1.09
     houſe
    1.00
    UnsafeEnabled
    0.95
     betweenstory
    0.94
     Meksiku
    0.93
     ་་
    0.91
     Houſe
    0.91
    InjectAttribute
    0.91
     Efq
    0.90
     ―――――
    0.90
    Act Density 0.145%

    No Known Activations