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

    Neuronpedia

    INDEX
    Explanations

    statements or questions about reasoning and motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.67
    yntaxException
    -0.62
    errHandler
    -0.56
    GenerationType
    -0.54
    олові
    -0.53
     referenties
    -0.51
    tvguidetime
    -0.50
    šanu
    -0.49
    apeno
    -0.49
    pergillus
    -0.49
    POSITIVE LOGITS
     why
    1.63
     reason
    1.34
    why
    1.31
     reasons
    1.20
     motivo
    1.15
     pourquoi
    1.15
     Why
    1.13
     WHY
    1.10
    Why
    1.09
     varför
    1.08
    Act Density 0.346%

    No Known Activations