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

    Neuronpedia

    INDEX
    Explanations

    statistical terminology and significance in research analysis

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

    Follows a verb "to be" and precedes a past participle

    np_acts-logits-general · gemini-2.0-flash

    conclusion determined by is/was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Used
    -0.63
    used
    -0.56
     USED
    -0.56
    Used
    -0.54
    ControllerAdvice
    -0.50
    Paginator
    -0.50
    saraba
    -0.50
     used
    -0.49
    engah
    -0.48
    Slut
    -0.46
    POSITIVE LOGITS
     determined
    0.94
     achieved
    0.90
     symbolized
    0.86
     signified
    0.83
     represented
    0.82
     protoimpl
    0.80
     représenté
    0.78
     accomplished
    0.78
     déterminé
    0.77
     measured
    0.77
    Act Density 0.805%

    No Known Activations