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

    Neuronpedia

    INDEX
    Explanations

    beginning and ending tokens in a sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portály
    -0.83
    oneofs
    -0.67
     RESOLUTION
    -0.63
     florales
    -0.60
    Portale
    -0.60
    COMPLE
    -0.59
     gescha
    -0.58
    tagem
    -0.58
    shadowOpacity
    -0.58
     Flagstaff
    -0.57
    POSITIVE LOGITS
    makeText
    0.70
    Якщо
    0.68
     SAC
    0.66
    Tikang
    0.65
    If
    0.63
    如果您
    0.62
    vido
    0.61
     look
    0.61
    UTC
    0.60
     If
    0.59
    Act Density 0.075%

    No Known Activations