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

    Neuronpedia

    INDEX
    Explanations

    elements related to group dynamics and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arez
    -0.15
    èª
    -0.14
    indr
    -0.14
    ÏĦά
    -0.14
    .eulerAngles
    -0.13
    .tp
    -0.13
    даÑİÑĤ
    -0.13
    elines
    -0.13
    panse
    -0.13
    891
    -0.13
    POSITIVE LOGITS
    bec
    0.49
     eventually
    0.48
     gradually
    0.46
     becoming
    0.46
     becomes
    0.45
     become
    0.44
     Eventually
    0.43
    Eventually
    0.41
     Bec
    0.41
     eventual
    0.41
    Act Density 0.129%

    No Known Activations