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

    Neuronpedia

    INDEX
    Explanations

    action verbs that indicate providing, managing, or calculating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     us
    -0.21
     itself
    -0.19
     himself
    -0.18
    avier
    -0.16
    etti
    -0.16
    612
    -0.14
    çIJ³
    -0.14
    yal
    -0.14
     Herrera
    -0.14
     herself
    -0.14
    POSITIVE LOGITS
     ourselves
    0.28
     selves
    0.17
    itches
    0.16
    PostBack
    0.15
    -Origin
    0.14
    üçük
    0.14
    οÏģ
    0.14
     Mash
    0.14
    ToProps
    0.14
    unately
    0.13
    Act Density 0.224%

    No Known Activations