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

    Neuronpedia

    INDEX
    Explanations

    words associated with weakness or timidity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehr
    -0.17
    addons
    -0.16
    EdgeInsets
    -0.15
    iegel
    -0.15
    iros
    -0.15
    jev
    -0.15
    erchant
    -0.14
    jeme
    -0.14
    llib
    -0.14
    elidir
    -0.14
    POSITIVE LOGITS
    åĩ¡
    0.18
    tee
    0.16
    ism
    0.16
    Spaces
    0.15
    ync
    0.14
     reversible
    0.14
    κοÏį
    0.14
    stance
    0.14
    pool
    0.13
    梨
    0.13
    Act Density 0.195%

    No Known Activations