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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific technical methods or skills

    oai_token-act-pair · gpt-3.5-turbo

    references to various methods or techniques across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pg
    -0.76
    oor
    -0.69
    isle
    -0.67
    riel
    -0.67
    arel
    -0.65
    gur
    -0.63
    emn
    -0.62
    estine
    -0.62
    appointed
    -0.62
    gran
    -0.61
    POSITIVE LOGITS
     techniques
    1.12
     technique
    1.07
    advertisement
    0.83
     Technique
    0.82
     Techniques
    0.82
     tricks
    0.81
     methods
    0.78
    ologies
    0.76
     chops
    0.73
     guiActiveUn
    0.73
    Act Density 0.017%

    No Known Activations