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

    Neuronpedia

    INDEX
    Explanations

    the suffix "st" in various forms, indicating superlatives or certain descriptive words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.73
     Yor
    -0.69
    tz
    -0.67
     whatsoever
    -0.61
     wit
    -0.60
     Yad
    -0.60
     TIME
    -0.60
    TD
    -0.59
    STON
    -0.59
     STAND
    -0.59
    POSITIVE LOGITS
    hetic
    0.87
    hetics
    0.83
    hesis
    0.83
    ectomy
    0.82
    ensibly
    0.81
    ertain
    0.80
    ogyn
    0.79
    ilion
    0.78
    agram
    0.78
    ray
    0.77
    Act Density 0.215%

    No Known Activations