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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to concepts of agency or action, particularly in a context of responsibility or offering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commune
    -0.16
     p
    -0.15
    amd
    -0.15
     resort
    -0.14
     trace
    -0.14
    andi
    -0.14
     заÑħ
    -0.14
    -0.14
    iveau
    -0.13
     comm
    -0.13
    POSITIVE LOGITS
    dba
    0.16
    ç¿°
    0.15
     Lesser
    0.15
    lass
    0.14
    ordo
    0.14
     dra
    0.14
    eco
    0.14
    CLUDING
    0.14
    ANEL
    0.14
    elyn
    0.14
    Act Density 0.069%

    No Known Activations