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

    Neuronpedia

    INDEX
    Explanations

    terms related to optimization and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leton
    -0.19
    ible
    -0.18
    eled
    -0.18
    icular
    -0.17
    eos
    -0.16
    ebe
    -0.16
    erate
    -0.16
    e
    -0.15
    ary
    -0.15
    uche
    -0.15
    POSITIVE LOGITS
    ally
    0.27
    istic
    0.23
    ised
    0.23
    istically
    0.22
    izers
    0.22
    izes
    0.21
    ISTIC
    0.20
    isation
    0.20
    ized
    0.20
    ality
    0.20
    Act Density 0.010%

    No Known Activations