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

    Neuronpedia

    INDEX
    Explanations

    phrases related to assumptions and the process of making judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifu
    -0.17
    å¾
    -0.16
    bud
    -0.15
    ideshow
    -0.15
    rella
    -0.15
    kke
    -0.15
     UIB
    -0.15
    ushi
    -0.14
    enal
    -0.14
    vince
    -0.14
    POSITIVE LOGITS
     assumption
    0.93
     assume
    0.85
     assumed
    0.83
     assumptions
    0.83
     assumes
    0.79
     assum
    0.79
    assume
    0.74
     Ass
    0.73
     assuming
    0.72
    ass
    0.71
    Act Density 0.343%

    No Known Activations