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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to methodologies or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.87
    mos
    -0.73
    r
    -0.70
     LOG
    -0.70
    ر
    -0.69
    ar
    -0.67
    gar
    -0.67
    c
    -0.66
    rd
    -0.66
    </em>
    -0.66
    POSITIVE LOGITS
     techniques
    1.45
     Techniques
    1.44
    techniques
    1.28
    Techniques
    1.28
     Technique
    1.26
     TECHNIQUES
    1.24
     technique
    1.17
     itſelf
    1.14
     TECHNIQUE
    1.13
     Aene
    1.08
    Act Density 0.085%

    No Known Activations