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

    Neuronpedia

    INDEX
    Explanations

    instances of accountability and responsibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.21
     ::::::::
    -0.17
    ocker
    -0.16
     Downs
    -0.16
    ascript
    -0.15
    eeper
    -0.15
     nast
    -0.14
    ASTER
    -0.14
    _PATCH
    -0.14
    ripper
    -0.14
    POSITIVE LOGITS
    v
    0.16
     truly
    0.16
    _
    0.15
     _{}
    0.15
    ↵
    0.15
    oo
    0.15
     inherently
    0.15
    e
    0.15
    /is
    0.15
    0.15
    Act Density 0.509%

    No Known Activations