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

    Neuronpedia

    INDEX
    Explanations

    references to educational sessions and training programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èª
    -0.17
     rallies
    -0.16
    deo
    -0.15
    ansa
    -0.15
    elts
    -0.14
    imore
    -0.14
    apus
    -0.14
     rally
    -0.14
    ula
    -0.14
    pper
    -0.14
    POSITIVE LOGITS
     behalf
    0.39
     basis
    0.28
     occasion
    0.26
    basis
    0.24
     grounds
    0.24
    occasion
    0.22
     occasions
    0.22
    _basis
    0.20
     Basis
    0.18
    assis
    0.17
    Act Density 0.543%

    No Known Activations