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

    Neuronpedia

    INDEX
    Explanations

    expressions related to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.15
     yourselves
    -0.15
    andes
    -0.14
    даÑĤ
    -0.14
    InThe
    -0.14
    PLL
    -0.13
    onth
    -0.13
    eil
    -0.13
    367
    -0.13
    (the
    -0.13
    POSITIVE LOGITS
     his
    0.44
     seu
    0.40
     sua
    0.40
     her
    0.38
     seus
    0.38
     suas
    0.35
     their
    0.35
     seine
    0.33
     your
    0.32
     suo
    0.32
    Act Density 1.000%

    No Known Activations