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

    Neuronpedia

    INDEX
    Explanations

    Expressions of grief and loss in personal and collective contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     |--------------------------------------------------------------------------↵
    -0.15
     ::::::::
    -0.14
    ì§ĵ
    -0.13
     bele
    -0.13
    inium
    -0.13
    etine
    -0.13
    izu
    -0.13
    ία
    -0.13
    ancestor
    -0.13
    ávÄĽ
    -0.13
    POSITIVE LOGITS
     loss
    1.09
     lose
    0.95
     Loss
    0.93
    loss
    0.93
     lost
    0.92
    Loss
    0.90
     losing
    0.89
     losses
    0.89
    -loss
    0.86
     loses
    0.85
    Act Density 0.361%

    No Known Activations