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

    Neuronpedia

    INDEX
    Explanations

    terms related to diplomatic and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Armour
    -0.19
     Klo
    -0.16
    oud
    -0.16
    edla
    -0.15
    ounding
    -0.14
    ä¼
    -0.14
    ì¦Ī
    -0.14
    Linear
    -0.14
    subclass
    -0.14
     HeaderComponent
    -0.14
    POSITIVE LOGITS
    _KP
    0.16
    ahead
    0.15
    èī¯
    0.15
     ãĤŃãĥ£
    0.14
    dbl
    0.14
    _perms
    0.14
    ÙĪاز
    0.14
     ÙħØ«
    0.14
    duto
    0.13
    è»
    0.13
    Act Density 0.151%

    No Known Activations