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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or capability

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

    rather alternatively instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſcher
    -0.51
    troppo
    -0.49
     Infór
    -0.48
    pulseira
    -0.47
    principalColumn
    -0.45
     Verſ
    -0.44
    iffance
    -0.44
    iſen
    -0.44
     gyhoeddwyd
    -0.43
    esgue
    -0.43
    POSITIVE LOGITS
     rather
    0.52
     alternatively
    0.48
     Rather
    0.47
    Rather
    0.46
     elseif
    0.45
    OrEqualTo
    0.43
    rather
    0.41
     defaultstate
    0.41
     instead
    0.40
     Alternatively
    0.39
    Act Density 0.020%

    No Known Activations