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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating a direction or an outcome, particularly in the context of decision-making or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fony
    -0.17
    EDI
    -0.16
    uw
    -0.15
    OnClick
    -0.14
    imeo
    -0.14
    aser
    -0.14
    ney
    -0.14
    arie
    -0.14
    use
    -0.14
     lep
    -0.14
    POSITIVE LOGITS
    625
    0.18
    gers
    0.16
    aina
    0.15
    hunter
    0.14
    OSH
    0.14
    haft
    0.14
    LAY
    0.14
     us
    0.14
    leading
    0.14
    ç¥
    0.14
    Act Density 0.027%

    No Known Activations