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

    Neuronpedia

    INDEX
    Explanations

    expressions or phrases that indicate distinction or differentiation

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

    distinguish himself from others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adpleegd
    -0.46
     blackmail
    -0.44
     nawr
    -0.41
     RSSSF
    -0.40
     ї
    -0.37
    samt
    -0.37
     Zug
    -0.36
    wydd
    -0.35
     darauf
    -0.35
    paper
    -0.35
    POSITIVE LOGITS
     differentiates
    0.85
     differentiating
    0.82
     differentiate
    0.79
     Differenti
    0.72
    Differenti
    0.71
     uniqueness
    0.69
     differenti
    0.68
     unique
    0.67
     differentiation
    0.65
     distinguishes
    0.64
    Act Density 0.010%

    No Known Activations