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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the articulation of opinions or statements

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

    Something said or uttered

    np_acts-logits-general · gemini-2.0-flash

    saying things aloud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Naissance
    -0.59
    tagHelperRunner
    -0.57
     متعلقه
    -0.56
    expandindo
    -0.54
     stør
    -0.54
    SourceChecksum
    -0.53
    photobucket
    -0.51
    TagHelpers
    -0.51
     tiêu
    -0.51
    ladin
    -0.49
    POSITIVE LOGITS
     uttered
    0.98
     aloud
    0.79
     loud
    0.78
     spoken
    0.73
     louder
    0.71
     words
    0.70
    ंदीखरीदारी
    0.69
     verbally
    0.66
     utterances
    0.66
     speech
    0.66
    Act Density 0.403%

    No Known Activations