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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate opinions or subjective assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivent
    -0.17
    aldo
    -0.17
    qv
    -0.15
    ote
    -0.14
    oid
    -0.14
     Leigh
    -0.14
    alty
    -0.14
     Maher
    -0.14
    ent
    -0.13
    agnost
    -0.13
    POSITIVE LOGITS
    uter
    0.15
    uvian
    0.15
    ायन
    0.15
    iyon
    0.15
     Incoming
    0.14
    ação
    0.14
    λικά
    0.14
    orz
    0.14
    959
    0.14
    085
    0.13
    Act Density 0.005%

    No Known Activations