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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or claims followed by elaboration or explanation

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

    "Went on to"

    np_acts-logits-general · gemini-2.0-flash

    going on to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.67
     незавершена
    -0.62
     gynhyrchwyd
    -0.57
     оригіналу
    -0.57
    MessageTagHelper
    -0.56
     فريبيس
    -0.54
    xiety
    -0.54
     CreateTagHelper
    -0.52
    Personendaten
    -0.52
     виправивши
    -0.50
    POSITIVE LOGITS
     continuing
    0.50
     onward
    0.50
     continued
    0.48
     continue
    0.48
     continuant
    0.46
     continues
    0.46
     weiter
    0.45
     ongoing
    0.45
     prosegu
    0.45
    wpdb
    0.44
    Act Density 0.125%

    No Known Activations