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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating changes or fluctuations in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGO
    -0.17
    etto
    -0.15
    ml
    -0.15
     Gund
    -0.15
    acer
    -0.15
    pecified
    -0.15
     floats
    -0.15
    igo
    -0.14
    olla
    -0.14
    ont
    -0.14
    POSITIVE LOGITS
    BindingUtil
    0.18
    dÃŃ
    0.16
    exus
    0.15
     Ritch
    0.14
    dish
    0.14
    нина
    0.14
    Injector
    0.14
    oppers
    0.14
    aab
    0.14
    _perms
    0.14
    Act Density 0.085%

    No Known Activations