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

    Neuronpedia

    INDEX
    Explanations

    prepositions and references to inclusion within context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cephala
    -0.58
     
    -0.55
    <eos>
    -0.52
     Mr
    -0.45
    </em>
    -0.42
    /
    -0.42
    openha
    -0.42
    mathrm
    -0.41
    Mr
    -0.41
     sch
    -0.41
    POSITIVE LOGITS
     MonoBehaviour
    0.91
     propOrder
    0.89
     surla
    0.84
    يميديا
    0.82
    <bos>
    0.82
     незавершена
    0.82
    XmlAccessType
    0.78
     Vikipedi
    0.77
    ContentAlignment
    0.76
     useRef
    0.75
    Act Density 0.829%

    No Known Activations