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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating changes in circumstances or situations, particularly relating to improvement or deterioration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pert
    -0.16
    wend
    -0.15
    ubb
    -0.15
     pert
    -0.15
    UILT
    -0.14
    igo
    -0.14
    олеÑĤ
    -0.14
    ujet
    -0.14
    inces
    -0.14
    ãĤĤãĤĬ
    -0.14
    POSITIVE LOGITS
    оÑıн
    0.16
    -caption
    0.15
    alin
    0.15
    vel
    0.14
    воÑİ
    0.14
    voie
    0.14
    borne
    0.14
    anch
    0.14
     Episcopal
    0.13
    ensus
    0.13
    Act Density 0.125%

    No Known Activations