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

    Neuronpedia

    INDEX
    Explanations

    expressions of likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bress
    -0.78
    andaag
    -0.78
    ริง
    -0.73
     &[
    -0.71
     createStore
    -0.70
     وتسجيلات
    -0.70
    ldorf
    -0.68
     pstmt
    -0.67
     Audiodateien
    -0.67
     fermés
    -0.67
    POSITIVE LOGITS
     likely
    1.45
     Likely
    1.37
    Likely
    1.33
    likely
    1.31
    unlikely
    0.96
     unlikely
    0.91
    Likelihood
    0.91
     LIK
    0.91
    likelihood
    0.81
     Probable
    0.81
    Act Density 0.100%

    No Known Activations