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

    Neuronpedia

    INDEX
    Explanations

    terms related to health-related benefits or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argo
    -0.19
    poz
    -0.15
    IVAL
    -0.14
     Burnett
    -0.14
    vek
    -0.14
    walker
    -0.14
    ival
    -0.14
    arg
    -0.13
    аÑĢÑħ
    -0.13
     front
    -0.13
    POSITIVE LOGITS
    RIEND
    0.16
    inite
    0.15
    æĸ
    0.15
    hire
    0.15
     Äįe
    0.14
    595
    0.14
    _SECURE
    0.14
     dee
    0.14
    acute
    0.14
    teness
    0.14
    Act Density 0.010%

    No Known Activations