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

    Neuronpedia

    INDEX
    Explanations

    references to entities that are pluralized or enumerated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xfd
    -0.14
    θο
    -0.14
    aint
    -0.14
    де
    -0.13
    owl
    -0.13
    ãģĤãĤĬ
    -0.13
    OwnProperty
    -0.13
    tron
    -0.13
    Gratis
    -0.13
    isc
    -0.13
    POSITIVE LOGITS
    curity
    0.24
     particular
    0.21
    -ÑĤо
    0.20
    quence
    0.19
    ched
    0.17
     kinds
    0.17
    omba
    0.17
    cond
    0.17
    OMB
    0.16
    acco
    0.16
    Act Density 0.040%

    No Known Activations