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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bress
    -0.78
     pstmt
    -0.74
    dojo
    -0.72
     Familienname
    -0.71
    ริง
    -0.70
     &[
    -0.69
     fermés
    -0.69
    Datuak
    -0.68
     createStore
    -0.68
    addPreferredGap
    -0.67
    POSITIVE LOGITS
     likely
    1.36
     Likely
    1.35
    Likely
    1.29
    likely
    1.25
     LIK
    0.90
    unlikely
    0.88
     unlikely
    0.86
    Likelihood
    0.83
    دانشنامهٔ
    0.80
    lihood
    0.79
    Act Density 0.098%

    No Known Activations