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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive sentiment and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /trunk
    -0.16
    é¨ĵ
    -0.15
    enger
    -0.15
    abox
    -0.15
     corners
    -0.14
     Fold
    -0.14
    iteur
    -0.14
    DRV
    -0.14
     fists
    -0.13
    ReuseIdentifier
    -0.13
    POSITIVE LOGITS
    ermann
    0.17
     pos
    0.16
     Pos
    0.16
    è¢
    0.15
    iso
    0.15
     Sync
    0.15
    _dbg
    0.15
    CKER
    0.15
    awi
    0.14
    BuilderInterface
    0.14
    Act Density 0.032%

    No Known Activations