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

    Neuronpedia

    INDEX
    Explanations

    certain adjectives and verbs related to evaluation or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crosby
    -0.17
    ÏĩÏİ
    -0.16
     Burg
    -0.15
     Grades
    -0.15
    ANG
    -0.14
    anga
    -0.14
    urret
    -0.14
     Mang
    -0.14
    inic
    -0.14
     angi
    -0.13
    POSITIVE LOGITS
    ig
    1.00
    IG
    0.80
     ig
    0.77
     Ig
    0.75
    иг
    0.73
     IG
    0.71
    iga
    0.68
    ige
    0.68
    igs
    0.66
    igi
    0.63
    Act Density 0.152%

    No Known Activations