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

    Neuronpedia

    INDEX
    Explanations

    character traits and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æİ¥çĿĢ
    -0.16
    urtles
    -0.15
    IVO
    -0.15
    ñana
    -0.15
    egers
    -0.14
    ParameterValue
    -0.14
    cke
    -0.14
    ¶Į
    -0.14
    Õ¡
    -0.14
    å¡ļ
    -0.14
    POSITIVE LOGITS
     nomin
    0.16
    och
    0.16
     Ferd
    0.16
    kar
    0.14
    âĺĨ
    0.14
     due
    0.13
    oom
    0.13
     Haupt
    0.13
     crash
    0.13
    rix
    0.13
    Act Density 0.002%

    No Known Activations