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

    Neuronpedia

    INDEX
    Explanations

    names and titles associated with individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \uc
    -0.15
    luž
    -0.14
    aurant
    -0.14
    ction
    -0.14
    ounge
    -0.14
    DIST
    -0.14
    yh
    -0.13
    ulling
    -0.13
    ibox
    -0.13
    олÑİ
    -0.13
    POSITIVE LOGITS
     Skip
    0.21
     Short
    0.20
    Short
    0.19
     Doc
    0.19
     Professor
    0.19
    Skip
    0.19
    Big
    0.19
     Chief
    0.18
     Dynam
    0.18
     Legs
    0.18
    Act Density 0.113%

    No Known Activations