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

    Neuronpedia

    INDEX
    Explanations

    mention of techniques or methods related to various contexts

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

    technique or techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.71
    #+#
    -0.66
    󠁮
    -0.66
     queſta
    -0.61
     zwiſchen
    -0.60
     ſeine
    -0.59
     müſſen
    -0.59
     zuſammen
    -0.57
     $_(
    -0.57
    ﹧
    -0.57
    POSITIVE LOGITS
     techniques
    1.55
     technique
    1.50
    Techniques
    1.41
    techniques
    1.41
     Techniques
    1.38
     Technique
    1.34
    Technique
    1.34
     TECHNIQUES
    1.34
    technique
    1.30
     TECHNIQUE
    1.27
    Act Density 0.015%

    No Known Activations