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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate primary focus or main ideas in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dulce
    -0.64
    Action
    -0.60
     Fass
    -0.59
    від
    -0.58
    zu
    -0.57
    R
    -0.57
    itope
    -0.57
    渍
    -0.57
    C
    -0.57
    óa
    -0.56
    POSITIVE LOGITS
     mainly
    2.88
     primarily
    2.81
    primarily
    2.63
     Mainly
    2.62
     mostly
    2.56
    mainly
    2.53
    Mainly
    2.46
    Mostly
    2.43
     Mostly
    2.43
     Primarily
    2.42
    Act Density 0.069%

    No Known Activations