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

    Neuronpedia

    INDEX
    Explanations

    terms related to assistance or support roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    รà¸Ńà¸ĩ
    -0.17
    paces
    -0.17
    lette
    -0.16
    ảo
    -0.16
    assic
    -0.16
    ças
    -0.15
    ething
    -0.15
    lettes
    -0.15
    recision
    -0.15
    assed
    -0.15
    POSITIVE LOGITS
    ive
    0.35
    ances
    0.21
    ants
    0.21
    IVE
    0.19
    ivec
    0.19
    /support
    0.18
    ively
    0.18
    ance
    0.16
    ilia
    0.16
    itude
    0.16
    Act Density 0.028%

    No Known Activations