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

    Neuronpedia

    INDEX
    Explanations

    negative expressions and denial

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

    Followed by "only", "registered", or "interested"

    np_acts-logits-general · gemini-2.0-flash

    not only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.51
     utafitiHapana
    -0.51
    发表于
    -0.49
    windowFixed
    -0.47
    WriteAttribute
    -0.46
    isissez
    -0.46
    ötä
    -0.46
    ',(
    -0.45
    ("]");
    -0.44
     Polres
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.78
     autorytatywna
    0.69
     rispar
    0.67
     exactly
    0.67
     mince
    0.65
     épar
    0.65
    ="@+
    0.64
    ($__
    0.64
     shy
    0.63
     exatamente
    0.62
    Act Density 0.276%

    No Known Activations