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

    Neuronpedia

    INDEX
    Explanations

    terms related to organizational policies and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    794
    -0.17
     Loft
    -0.15
     Mae
    -0.14
    orna
    -0.14
     PROCUREMENT
    -0.13
    actor
    -0.13
     RG
    -0.13
    _pol
    -0.13
    ateur
    -0.13
     Spar
    -0.12
    POSITIVE LOGITS
    uhn
    0.17
    lah
    0.16
    ebin
    0.16
    efault
    0.16
    yal
    0.15
    .YesNo
    0.14
    usalem
    0.14
    incinn
    0.14
    jezd
    0.14
    lander
    0.14
    Act Density 0.008%

    No Known Activations