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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and metrics related to the effectiveness of interventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arry
    -0.18
    stat
    -0.15
    ³
    -0.15
    mos
    -0.15
    razier
    -0.15
    uary
    -0.15
    canonical
    -0.14
    nat
    -0.14
     overall
    -0.14
     Overall
    -0.14
    POSITIVE LOGITS
    rud
    0.17
    ibir
    0.17
    ikon
    0.16
    iber
    0.15
    еÑĢб
    0.15
    eson
    0.15
    caff
    0.15
    antino
    0.14
     only
    0.14
    SSIP
    0.13
    Act Density 0.211%

    No Known Activations