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

    Neuronpedia

    INDEX
    Explanations

    terms related to avoidance and negative characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indle
    -0.22
    plib
    -0.16
    readcr
    -0.15
    dge
    -0.14
    ombs
    -0.14
     ФедеÑĢаÑĨии
    -0.14
     mu
    -0.14
    ometric
    -0.14
    _fwd
    -0.13
    .pair
    -0.13
    POSITIVE LOGITS
    pell
    0.17
    borg
    0.15
    íĮĮ
    0.15
    æķ¢
    0.15
     Britann
    0.14
    çĺ
    0.14
    ertino
    0.14
    iosa
    0.14
    MAP
    0.13
    ixer
    0.13
    Act Density 0.000%

    No Known Activations