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

    Neuronpedia

    INDEX
    Explanations

    intensifiers and modifiers that emphasize qualities or descriptions

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

    Adverbs/qualifiers of varying intensity

    np_acts-logits-general · gemini-2.0-flash

    intensifiers followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financeira
    -0.67
     térmico
    -0.64
     urbana
    -0.60
    both
    -0.59
    Hentet
    -0.56
     financeiro
    -0.56
     amnesty
    -0.54
     tritium
    -0.52
     africaine
    -0.51
     betegs
    -0.51
    POSITIVE LOGITS
    lynol
    0.80
    tvguidetime
    0.76
    */;
    0.72
    olesale
    0.71
    iterranean
    0.68
    "]="
    0.68
     positive
    0.67
     valid
    0.66
    ividual
    0.65
     ')
    0.65
    Act Density 0.290%

    No Known Activations