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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and phrases that indicate potential outcomes or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mens
    -0.16
     boÄŁ
    -0.15
    ãĥªãĥ³
    -0.15
     hữu
    -0.15
    _DISK
    -0.14
     McA
    -0.14
     kans
    -0.14
    imson
    -0.14
    باد
    -0.14
    arnation
    -0.14
    POSITIVE LOGITS
    366
    0.15
     Fle
    0.14
     at
    0.13
    /if
    0.13
    48
    0.13
     vivo
    0.13
    ozem
    0.13
    484
    0.13
    216
    0.13
     considering
    0.13
    Act Density 0.107%

    No Known Activations