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

    Neuronpedia

    INDEX
    Explanations

    language related to threats and communication issues in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     baiser
    -0.17
     reb
    -0.16
    ignon
    -0.14
    emic
    -0.14
    ERNEL
    -0.13
    flu
    -0.13
    ÑĢез
    -0.13
    raç
    -0.13
     cube
    -0.13
    plex
    -0.13
    POSITIVE LOGITS
    icari
    0.15
     dash
    0.15
    inta
    0.15
    à¥Ĥà¤ļन
    0.15
    æĨ
    0.14
     gele
    0.14
     å§
    0.14
    nav
    0.14
    ifa
    0.13
    avanaugh
    0.13
    Act Density 0.341%

    No Known Activations