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

    Neuronpedia

    INDEX
    Explanations

    references to rankings or evaluations of different subjects

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

    preceding adjectives

    np_acts-logits-general · gemini-2.0-flash

    adjectives describing qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vulgares
    -0.63
    Effective
    -0.62
    saraba
    -0.57
    effective
    -0.57
     scelte
    -0.56
     føl
    -0.55
     particulières
    -0.54
     aggiun
    -0.54
     connues
    -0.53
     EconPapers
    -0.52
    POSITIVE LOGITS
     heavily
    0.99
     highly
    0.84
     externally
    0.79
     lightly
    0.76
     fully
    0.75
     BorderSide
    0.74
     politically
    0.74
     largely
    0.74
     extensively
    0.73
     socially
    0.73
    Act Density 0.374%

    No Known Activations