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

    Neuronpedia

    INDEX
    Explanations

    specific adjectives and descriptors related to objects or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apor
    -0.17
    alam
    -0.16
    arak
    -0.15
    _constructor
    -0.14
    aran
    -0.14
    ektor
    -0.13
    ÛĮÙĨ
    -0.13
    ãĥ¼ãĤ¯
    -0.13
    ection
    -0.12
     NOTIFY
    -0.12
    POSITIVE LOGITS
    ailability
    0.16
    ĤŃ
    0.15
     Dove
    0.15
    ãĤ¤ãĥ¤
    0.14
    nou
    0.14
    aterno
    0.14
    ÄĻd
    0.14
    heimer
    0.14
    psz
    0.14
    apos
    0.14
    Act Density 0.050%

    No Known Activations