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

    Neuronpedia

    INDEX
    Explanations

    words related to power dynamics and agency in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    433
    -0.16
    981
    -0.16
    glyphicon
    -0.14
    533
    -0.14
     Integral
    -0.14
     integral
    -0.14
    uler
    -0.13
     Zus
    -0.13
    elt
    -0.13
     supporting
    -0.13
    POSITIVE LOGITS
    iran
    0.15
    ldr
    0.14
    AccessException
    0.14
    ìĿ´ìĬ¤
    0.14
    agini
    0.14
    [Index
    0.14
    amaz
    0.14
    ancellable
    0.14
    ngo
    0.14
    [first
    0.14
    Act Density 0.007%

    No Known Activations