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

    Neuronpedia

    INDEX
    Explanations

    references to the "Arc" concept in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tgt
    -0.16
     Dud
    -0.15
    .slim
    -0.15
    ìĹŃ
    -0.15
    oir
    -0.15
     McCabe
    -0.15
    Č↵
    -0.14
    apg
    -0.14
    EE
    -0.14
    afone
    -0.14
    POSITIVE LOGITS
    adia
    0.32
    uate
    0.27
    adian
    0.26
    ady
    0.24
    angel
    0.23
    ansas
    0.23
    adians
    0.21
    adius
    0.21
    áng
    0.21
    aded
    0.20
    Act Density 0.010%

    No Known Activations