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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.73
    CppCodeGen
    -0.70
     endforeach
    -0.66
    UnusedPrivate
    -0.65
    ensioni
    -0.65
    UrlResolution
    -0.64
    ArrowToggle
    -0.64
     myſelf
    -0.64
     dares
    -0.63
    stander
    -0.63
    POSITIVE LOGITS
     sounded
    0.58
     sounds
    0.56
     pretty
    0.55
     suffice
    0.55
     sound
    0.54
     solve
    0.53
     mean
    0.53
     оригіналу
    0.52
    pretty
    0.51
    TagMode
    0.50
    Act Density 0.360%

    No Known Activations