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

    Neuronpedia

    INDEX
    Explanations

    instances of repeated phrases or contextual references with significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anja
    -0.16
    seau
    -0.15
    alo
    -0.15
    acier
    -0.14
    anto
    -0.14
    stones
    -0.14
    Uniform
    -0.14
    Snow
    -0.14
    snow
    -0.14
    çĩ
    -0.14
    POSITIVE LOGITS
    avage
    0.16
     exchange
    0.16
     lie
    0.15
    ibling
    0.15
    isku
    0.15
    ойно
    0.15
     ga
    0.15
     Lie
    0.15
     internal
    0.14
     Hay
    0.14
    Act Density 0.015%

    No Known Activations