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

    Neuronpedia

    INDEX
    Explanations

    terms related to approval processes and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ionage
    -0.76
     Abyss
    -0.63
    utra
    -0.63
    ibrary
    -0.61
     Sins
    -0.61
     gou
    -0.60
    arks
    -0.59
     Tale
    -0.59
    si
    -0.59
    oise
    -0.59
    POSITIVE LOGITS
     unanimously
    1.19
     by
    1.06
     academ
    0.86
    animous
    0.81
     approved
    0.75
    approved
    0.71
     approval
    0.71
     muster
    0.70
     uncond
    0.70
     Parenthood
    0.68
    Act Density 0.039%

    No Known Activations