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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuation, transition, or progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal challenges and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.71
    agen
    -0.67
    enance
    -0.63
    kamp
    -0.63
    ves
    -0.62
    thood
    -0.62
    OWS
    -0.61
    £
    -0.61
    ç¥ŀ
    -0.60
    antly
    -0.59
    POSITIVE LOGITS
     besides
    0.88
     namely
    0.80
     viz
    0.79
     ranging
    0.76
    EStreamFrame
    0.75
     moreover
    0.75
     maybe
    0.72
     none
    0.72
     nowhere
    0.70
    maybe
    0.69
    Act Density 0.445%

    No Known Activations