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

    Neuronpedia

    INDEX
    Explanations

    complex sentence structures and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "and the"

    np_acts-logits-general · gemini-2.0-flash

    lack of ability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoField
    -0.80
    LEncoder
    -0.64
    JoinTable
    -0.58
     oprot
    -0.57
     varsa
    -0.56
     didst
    -0.55
    ArgsConstructor
    -0.54
    usercontent
    -0.53
    Geplaatst
    -0.53
     entregado
    -0.52
    POSITIVE LOGITS
     lack
    0.98
     inability
    0.82
     how
    0.82
     faptul
    0.72
    Lack
    0.71
     insistence
    0.71
     Lack
    0.67
     gebre
    0.66
     ability
    0.66
     عدم
    0.65
    Act Density 0.422%

    No Known Activations