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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal relationships and quirky dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.16
    imas
    -0.15
    laden
    -0.15
    ãĢĢãĥİ
    -0.15
    ιÏİν
    -0.14
     shalt
    -0.14
    ãĥ»ãĥ»ãĥ»↵↵
    -0.14
     nebu
    -0.14
    è²Į
    -0.14
    bru
    -0.14
    POSITIVE LOGITS
     Miz
    0.18
     ’
    0.17
    fol
    0.16
     get
    0.16
     gonna
    0.15
     folks
    0.15
     tek
    0.14
    chos
    0.14
     kin
    0.14
     crit
    0.14
    Act Density 0.128%

    No Known Activations