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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters typical in programming or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oir
    -0.19
     contrasting
    -0.15
    _rng
    -0.14
     Ash
    -0.14
     contrasts
    -0.14
     blindness
    -0.14
     rise
    -0.14
    .Binding
    -0.13
     dramatic
    -0.13
    irm
    -0.13
    POSITIVE LOGITS
     Manning
    0.16
    agara
    0.16
     Marion
    0.15
     îł
    0.14
    erset
    0.14
    elm
    0.14
    asan
    0.14
    ElementType
    0.14
    abbo
    0.14
    Ïħνα
    0.14
    Act Density 0.003%

    No Known Activations