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

    Neuronpedia

    INDEX
    Explanations

    the word "like" or its variations in context

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

    Comes before "that," "fiber," "CP," or similar

    np_acts-logits-general · gemini-2.0-flash

    for example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.60
    parsedMessage
    -0.57
    hip
    -0.55
     raiſ
    -0.54
     ſame
    -0.53
     feveral
    -0.52
     ſy
    -0.51
     ſuch
    -0.51
     Jefus
    -0.50
     XNUMX
    -0.49
    POSITIVE LOGITS
     ours
    0.85
     those
    0.85
    DockStyle
    0.81
    extAlignment
    0.79
     misalnya
    0.72
     this
    0.70
    เดียว
    0.70
     like
    0.70
     Мексичка
    0.69
     these
    0.68
    Act Density 0.151%

    No Known Activations