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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the significance or prevalence of certain characteristics, outcomes, or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     both
    -0.73
    moveToFirst
    -0.72
     muitas
    -0.72
    both
    -0.68
     many
    -0.67
     sometimes
    -0.63
     многих
    -0.62
     most
    -0.61
     muchas
    -0.61
    many
    -0.61
    POSITIVE LOGITS
    цездатний
    0.73
     comprised
    0.73
     consisting
    0.72
     devoted
    0.71
     consisted
    0.70
     consists
    0.68
     focused
    0.67
     composed
    0.65
    UserScript
    0.65
    InitStruct
    0.64
    Act Density 0.358%

    No Known Activations