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

    Neuronpedia

    INDEX
    Explanations

    mentions of choices or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roll
    -0.16
    urgeon
    -0.16
    <Option
    -0.16
    oras
    -0.15
    foon
    -0.15
    orer
    -0.15
    <dyn
    -0.14
    าะ
    -0.14
    lesi
    -0.14
    _optional
    -0.14
    POSITIVE LOGITS
    ality
    0.29
    nal
    0.24
    als
    0.22
    ally
    0.21
    nel
    0.20
     available
    0.19
    ning
    0.19
    ALLY
    0.18
    nement
    0.17
    :selected
    0.17
    Act Density 0.061%

    No Known Activations