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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating usefulness and helpfulness of information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollower
    -0.15
    еÑĢÑĮ
    -0.14
    ÃĸL
    -0.14
    ì¹Ļ
    -0.14
    acas
    -0.14
    reau
    -0.14
     Incontri
    -0.14
     Güven
    -0.13
    nton
    -0.13
    ABCDEFGHI
    -0.13
    POSITIVE LOGITS
     useful
    0.45
     helpful
    0.41
     valuable
    0.39
     beneficial
    0.35
     handy
    0.34
     helf
    0.34
     Useful
    0.33
     invaluable
    0.32
     hữu
    0.30
    use
    0.30
    Act Density 0.151%

    No Known Activations