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

    Neuronpedia

    INDEX
    Explanations

    phrases and sentences indicating reaching a specific stage or level of a process or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating varying conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mask
    -0.75
     Deer
    -0.70
    fml
    -0.67
    apult
    -0.66
    Chel
    -0.63
    thal
    -0.61
     Scythe
    -0.60
     Bees
    -0.60
    geist
    -0.60
    oor
    -0.59
    POSITIVE LOGITS
    upon
    1.15
    soever
    0.94
    abouts
    0.82
     electors
    0.73
     astronauts
    0.68
     volunteers
    0.68
     respondents
    0.67
     averages
    0.66
     crowds
    0.65
     people
    0.65
    Act Density 0.071%

    No Known Activations