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

    Neuronpedia

    INDEX
    Explanations

    various forms of dashes and hyphens indicating breaks or pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    []
    -0.60
     فريبيس
    -0.55
     Houſe
    -0.55
     kolei
    -0.54
     unary
    -0.53
    textsc
    -0.53
     honom
    -0.53
    duled
    -0.52
    *",
    -0.51
     psp
    -0.51
    POSITIVE LOGITS
    verwijspagina
    0.84
     although
    0.82
     ujednoznacz
    0.81
    __':
    0.77
     including
    0.75
    although
    0.74
     disambiguazione
    0.74
     albeit
    0.74
     mxArray
    0.73
     perhaps
    0.73
    Act Density 0.212%

    No Known Activations