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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating logical rationale or reasoning for actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sharedInstance
    -0.17
    ogui
    -0.17
    ientos
    -0.17
    rava
    -0.17
    aptors
    -0.15
    ENCHMARK
    -0.14
    ots
    -0.14
    laz
    -0.14
    isma
    -0.14
    stered
    -0.14
    POSITIVE LOGITS
    cape
    0.17
    lessly
    0.15
    vais
    0.15
    \modules
    0.15
     Cape
    0.14
    arg
    0.14
     cref
    0.14
    éĢ
    0.14
    ifter
    0.14
    79
    0.14
    Act Density 0.012%

    No Known Activations