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

    Neuronpedia

    INDEX
    Explanations

    negative constructions and suggestions for avoiding certain behaviors or attitudes

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

    try to avoid negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁴
    -0.59
    rungsseite
    -0.49
    SequentialGroup
    -0.47
     cuja
    -0.45
    mson
    -0.44
     okuyayım
    -0.43
     potenciales
    -0.43
    lorette
    -0.43
     voeten
    -0.43
    capai
    -0.42
    POSITIVE LOGITS
    awtextra
    0.45
    SharedDtor
    0.39
    ))}
    0.38
     PyLong
    0.38
    #
    0.38
    Bisous
    0.37
    enderror
    0.37
    ');?>
    0.37
     GoogleFonts
    0.36
    _));
    0.36
    Act Density 0.065%

    No Known Activations