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

    Neuronpedia

    INDEX
    Explanations

    instances of actions involving conducting, facilitating, or performing by specific individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adil
    -0.17
    MeasureSpec
    -0.17
    munition
    -0.17
    deniz
    -0.15
    brero
    -0.15
    TEGR
    -0.15
    ynom
    -0.14
    нен
    -0.14
    ipeline
    -0.14
    aiser
    -0.14
    POSITIVE LOGITS
     con
    0.15
     rein
    0.14
    itre
    0.14
     Hast
    0.13
    orte
    0.13
    cls
    0.13
    CHAIN
    0.13
    λμ
    0.13
     shaking
    0.13
    .contentView
    0.13
    Act Density 0.261%

    No Known Activations