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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing absence or presence of individuals and their emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foy
    -0.16
    indered
    -0.15
    antan
    -0.14
     Unsupported
    -0.14
    owied
    -0.13
    ibri
    -0.13
     Supported
    -0.13
     åħ
    -0.13
    iddled
    -0.13
    \Response
    -0.13
    POSITIVE LOGITS
     present
    0.52
     around
    0.42
     Present
    0.36
     presente
    0.35
     Around
    0.32
    Around
    0.31
     there
    0.31
    present
    0.31
     nearby
    0.31
    around
    0.30
    Act Density 0.254%

    No Known Activations