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

    Neuronpedia

    INDEX
    Explanations

    phrases that express subjective evaluations or judgments about situations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nichts
    -0.61
    ranslated
    -0.60
     whofe
    -0.60
     portata
    -0.60
    everyone
    -0.59
    everybody
    -0.59
    loit
    -0.58
     Dat
    -0.58
     Emblem
    -0.58
     colpa
    -0.57
    POSITIVE LOGITS
    __*/
    0.81
    __(/*!
    0.54
    bkz
    0.54
    LikeLike
    0.52
     ldc
    0.52
    DataContract
    0.52
    httphttps
    0.52
    JspWriter
    0.51
    TargetException
    0.51
     Процитовано
    0.51
    Act Density 0.209%

    No Known Activations