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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opposition or resistance to a subject or issue

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

    "against"

    np_acts-logits-general · gemini-2.0-flash

    against or opposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utnik
    -0.56
     newBuilder
    -0.55
     kapcsolat
    -0.52
    Tils
    -0.51
    eches
    -0.51
    õi
    -0.51
    اخ
    -0.50
    談社
    -0.50
     Hickey
    -0.48
    Lun
    -0.48
    POSITIVE LOGITS
    against
    0.95
     against
    0.94
    Against
    0.87
     Against
    0.86
     AGAINST
    0.85
    lihood
    0.69
    SizeF
    0.68
     odds
    0.66
     gegen
    0.65
    WriteTagHelper
    0.64
    Act Density 0.231%

    No Known Activations