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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achieving goals or reaching a particular destination

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating success or achievement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.68
     EVENTS
    -0.64
     Juda
    -0.63
    flex
    -0.61
    =#
    -0.59
     expressions
    -0.59
     intens
    -0.59
     elastic
    -0.58
     backdrop
    -0.57
     recurring
    -0.57
    POSITIVE LOGITS
    uberty
    0.83
     unsc
    0.75
    ozo
    0.74
    tten
    0.74
     Forbes
    0.72
    ophys
    0.71
     undet
    0.70
    istine
    0.70
     Unloaded
    0.69
    ellen
    0.68
    Act Density 0.095%

    No Known Activations