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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reports or claims about events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olesterol
    -0.86
    ĸļ
    -0.85
    alez
    -0.82
    chart
    -0.79
    claimer
    -0.78
    tsky
    -0.78
    hesis
    -0.75
    ãĤŃ
    -0.75
    ula
    -0.75
    hes
    -0.73
    POSITIVE LOGITS
     impending
    0.99
     sightings
    0.99
     layoffs
    0.84
     rampant
    0.84
     imminent
    0.84
     sporadic
    0.81
     suicides
    0.81
     leaks
    0.80
     casualties
    0.80
     widespread
    0.80
    Act Density 0.094%

    No Known Activations