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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate constraints or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    013
    -0.15
    127
    -0.15
    ista
    -0.15
    alone
    -0.14
    ctl
    -0.14
     alone
    -0.14
    amus
    -0.14
    elay
    -0.14
    IPP
    -0.14
    ulan
    -0.14
    POSITIVE LOGITS
     Lace
    0.15
    uddy
    0.15
    çĴĥ
    0.14
    bÃŃr
    0.14
    nell
    0.14
    elop
    0.14
     Bened
    0.13
     flagship
    0.13
     Sinai
    0.13
     Nor
    0.13
    Act Density 0.073%

    No Known Activations