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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relative positions (such as "above" and "below")

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cal
    -0.71
    Portail
    -0.68
    riwal
    -0.66
    er
    -0.64
     conv
    -0.64
    man
    -0.63
    ClickListener
    -0.63
    ril
    -0.63
    eral
    -0.60
     cal
    -0.59
    POSITIVE LOGITS
     ABOVE
    2.18
     Above
    2.17
    Above
    2.09
    above
    2.06
     above
    2.05
    ABOVE
    2.00
    bove
    1.79
     BELOW
    1.61
     Below
    1.51
    below
    1.48
    Act Density 0.078%

    No Known Activations