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

    Neuronpedia

    INDEX
    Explanations

    phrases that express recommendations or things that should not be missed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ráž
    -0.18
    ungal
    -0.16
    ifar
    -0.16
    _Impl
    -0.16
    /preferences
    -0.15
    ADS
    -0.15
     Scatter
    -0.15
    оÑģÑĤаÑĤ
    -0.15
    æij©
    -0.14
    estring
    -0.14
    POSITIVE LOGITS
     missed
    0.71
    miss
    0.65
     miss
    0.59
     Miss
    0.57
     misses
    0.56
    Miss
    0.54
    _miss
    0.47
     MISS
    0.47
    MISS
    0.42
     missing
    0.42
    Act Density 0.065%

    No Known Activations