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

    Neuronpedia

    INDEX
    Explanations

    terms relating to optimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ible
    -0.19
    leton
    -0.19
    eled
    -0.19
    erate
    -0.16
    eos
    -0.16
    ibles
    -0.16
    icular
    -0.16
    ey
    -0.15
    /*č↵
    -0.15
    eing
    -0.15
    POSITIVE LOGITS
    ally
    0.33
    ised
    0.30
    izes
    0.29
    ized
    0.28
    izing
    0.26
    izers
    0.26
    isation
    0.24
    istic
    0.24
    istically
    0.23
    ization
    0.23
    Act Density 0.008%

    No Known Activations