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

    Neuronpedia

    INDEX
    Explanations

    words related to goals, priorities, and focuses

    oai_token-act-pair · gpt-3.5-turbo

    expressions of priorities, goals, and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orks
    -0.70
     belonging
    -0.65
    aples
    -0.64
    acci
    -0.62
    uly
    -0.60
    necessary
    -0.60
    ignt
    -0.58
    heat
    -0.58
    reens
    -0.58
    ammy
    -0.58
    POSITIVE LOGITS
     consists
    0.80
    çīĪ
    0.80
     consisted
    0.79
    nings
    0.79
    ãĥķãĤ©
    0.76
     boils
    0.75
     revolves
    0.73
     takeaway
    0.72
     focuses
    0.71
     foray
    0.70
    Act Density 0.238%

    No Known Activations