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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news reports or communications about special events or offers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to special reports or notices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contag
    -0.69
     Merrill
    -0.68
     Cah
    -0.68
     breakup
    -0.65
     inev
    -0.63
     concussion
    -0.62
    ynthesis
    -0.61
     interstellar
    -0.60
     erosion
    -0.59
     ankles
    -0.58
    POSITIVE LOGITS
    itions
    0.85
    ortment
    0.73
    Special
    0.72
    roid
    0.71
    eus
    0.70
    ional
    0.69
    ãĤ¶
    0.67
    owship
    0.67
    asures
    0.66
    ras
    0.65
    Act Density 0.191%

    No Known Activations