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

    Neuronpedia

    INDEX
    Explanations

    references to various techniques and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riel
    -0.72
     gloom
    -0.68
    onen
    -0.67
    endar
    -0.66
    joy
    -0.64
    gets
    -0.61
    watching
    -0.61
     Gallagher
    -0.61
    engers
    -0.61
    vals
    -0.61
    POSITIVE LOGITS
    ologies
    1.23
     techniques
    0.98
     pioneered
    0.90
     employed
    0.89
     utilized
    0.84
     tricks
    0.82
     technique
    0.82
     whereby
    0.82
    OLOGY
    0.79
     manuals
    0.78
    Act Density 0.052%

    No Known Activations