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

    Neuronpedia

    INDEX
    Explanations

    periods and open parentheses in code-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.69
    featureID
    -0.66
    erweise
    -0.65
    tably
    -0.65
     ")";
    -0.65
    ]='\
    -0.61
    niana
    -0.58
    endphp
    -0.57
    гл
    -0.56
    ̸
    -0.56
    POSITIVE LOGITS
    RemoveField
    0.71
    AndEndTag
    0.69
    AnchorStyles
    0.63
    0.61
     JpaRepository
    0.60
    MemoryWarning
    0.59
    CodeAttribute
    0.59
    JsonFormat
    0.59
    IAction
    0.59
    awtextra
    0.57
    Act Density 0.226%

    No Known Activations