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

    Neuronpedia

    INDEX
    Explanations

    HTML-style spacing and formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ures
    -0.15
     bordel
    -0.15
    enda
    -0.15
    abet
    -0.14
    ÑģÑĤан
    -0.14
    zel
    -0.14
    پس
    -0.14
    ps
    -0.14
    h
    -0.14
     Conce
    -0.14
    POSITIVE LOGITS
    çİ
    0.16
    antan
    0.15
    वर
    0.14
    withstanding
    0.14
    lingen
    0.14
    zsche
    0.14
    quiry
    0.14
    licate
    0.14
     diss
    0.14
    Ñĥж
    0.13
    Act Density 0.010%

    No Known Activations