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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community engagement and collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     us
    -0.22
    us
    -0.18
     himself
    -0.16
    ater
    -0.16
     itself
    -0.15
     Stevenson
    -0.15
    uis
    -0.15
    ator
    -0.14
    ilo
    -0.14
    avier
    -0.13
    POSITIVE LOGITS
     ourselves
    0.34
     selves
    0.19
    bsp
    0.19
    PostBack
    0.16
     abych
    0.16
    insula
    0.15
    üçük
    0.15
    anvas
    0.15
    eah
    0.15
    blink
    0.15
    Act Density 1.464%

    No Known Activations