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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to certainty and conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aret
    -0.15
    884
    -0.15
    BT
    -0.14
    itesse
    -0.14
     Shade
    -0.14
    083
    -0.14
    erus
    -0.14
    metic
    -0.13
    cone
    -0.13
     rew
    -0.13
    POSITIVE LOGITS
    ymm
    0.18
     art
    0.17
    enth
    0.16
    hev
    0.16
    @api
    0.15
     баз
    0.15
     Cas
    0.14
     bas
    0.14
    GD
    0.14
    edl
    0.14
    Act Density 0.009%

    No Known Activations