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

    Neuronpedia

    INDEX
    Explanations

    subject pronouns and references to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToObject
    -0.17
    ợ
    -0.15
    anol
    -0.15
    ÌĢ
    -0.14
    ersh
    -0.14
     ÑĥÑģÑĤ
    -0.14
    én
    -0.14
    è¦ģ
    -0.14
    141
    -0.14
    ForResult
    -0.14
    POSITIVE LOGITS
     loose
    0.32
     into
    0.26
     Loose
    0.25
     alone
    0.25
     know
    0.23
     be
    0.22
     slide
    0.22
     onto
    0.20
     slip
    0.19
     Slide
    0.18
    Act Density 0.056%

    No Known Activations