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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce examples or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -1.05
    AndEndTag
    -0.90
    Diwedd
    -0.83
     cdti
    -0.79
     Majefty
    -0.73
     Houſe
    -0.72
     itſelf
    -0.71
    InjectAttribute
    -0.70
    ⓧ
    -0.70
    ่านั้น
    -0.70
    POSITIVE LOGITS
    :
    0.91
     consider
    0.67
     imagine
    0.65
     when
    0.63
     The
    0.58
     When
    0.56
     if
    0.55
     suppose
    0.55
     Suppose
    0.55
     the
    0.53
    Act Density 0.173%

    No Known Activations