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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that denote a particular quality or characteristic, often related to behavior or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restTemplate
    -0.60
    لينكات
    -0.59
     referenties
    -0.56
    tology
    -0.56
     跳转至
    -0.56
     وتسجيلات
    -0.56
     kaynağından
    -0.55
    ército
    -0.55
     samfun
    -0.55
    iastes
    -0.55
    POSITIVE LOGITS
    ish
    1.23
    ISH
    0.98
    ishly
    0.82
    ishness
    0.82
    ishing
    0.77
    ished
    0.70
     ſur
    0.69
    iſh
    0.67
    ishes
    0.66
     trim
    0.63
    Act Density 0.062%

    No Known Activations