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

    Neuronpedia

    INDEX
    Explanations

    words indicating strength or efficacy related to substances or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.14
    vis
    -0.14
    apper
    -0.14
    undi
    -0.13
     principal
    -0.13
    acter
    -0.13
    skirts
    -0.13
    ç°
    -0.13
    -me
    -0.13
     Dunn
    -0.13
    POSITIVE LOGITS
    elm
    0.16
    ãĥ¼ãĥĹ
    0.15
    inue
    0.14
    inea
    0.14
    rego
    0.14
    æłª
    0.14
    insula
    0.14
    achi
    0.14
     cleared
    0.13
    ÃŃg
    0.13
    Act Density 0.002%

    No Known Activations