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

    Neuronpedia

    INDEX
    Explanations

    references to statements and group dynamics, especially in contexts involving support or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.63
     Référence
    -0.61
     himself
    -0.58
    Havolalar
    -0.56
    antMatchers
    -0.55
    Tracce
    -0.55
     wife
    -0.54
    cèse
    -0.53
     وتسجيلات
    -0.53
    felf
    -0.52
    POSITIVE LOGITS
     themselves
    1.60
    Their
    1.39
     collectively
    1.35
    themselves
    1.34
     their
    1.32
    their
    1.25
     Their
    1.25
    各自
    1.24
     yourselves
    1.18
    それぞれ
    1.11
    Act Density 0.596%

    No Known Activations