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

    Neuronpedia

    INDEX
    Explanations

    words related to freshness or newness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    si
    -0.18
    tion
    -0.18
    tx
    -0.18
    ean
    -0.17
    ys
    -0.17
    té
    -0.17
    sap
    -0.17
    hai
    -0.17
    e
    -0.16
    ta
    -0.16
    POSITIVE LOGITS
    hest
    0.31
    coes
    0.28
    cos
    0.26
    her
    0.24
    coe
    0.22
    cob
    0.22
    cura
    0.21
    nel
    0.20
    co
    0.19
    coln
    0.18
    Act Density 0.006%

    No Known Activations