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

    Neuronpedia

    INDEX
    Explanations

    details related to attachments and connections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fillType
    -0.16
    ĵn
    -0.16
    ofire
    -0.15
    otten
    -0.15
    _HINT
    -0.15
     Craw
    -0.14
    _marshall
    -0.14
    CallCheck
    -0.14
    -cache
    -0.14
    ersen
    -0.13
    POSITIVE LOGITS
     cord
    0.21
     poles
    0.21
     ropes
    0.21
     ties
    0.20
     pole
    0.20
     clips
    0.20
     chains
    0.20
     strings
    0.20
     chain
    0.19
     tie
    0.19
    Act Density 0.173%

    No Known Activations