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

    Neuronpedia

    INDEX
    Explanations

    numerical percentage values

    oai_token-act-pair · gpt-3.5-turbo

    percentage symbols and related numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etr
    -0.73
     compr
    -0.72
    ITED
    -0.69
     debated
    -0.68
    pload
    -0.67
     framed
    -0.65
     scrambled
    -0.65
     stretched
    -0.64
    jected
    -0.64
     recons
    -0.64
    POSITIVE LOGITS
    -+
    0.76
    percent
    0.73
     ABV
    0.71
    %-
    0.71
    oyer
    0.71
    module
    0.70
    rate
    0.70
    xual
    0.70
    rowth
    0.69
    lust
    0.67
    Act Density 0.043%

    No Known Activations