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

    Neuronpedia

    INDEX
    Explanations

    emotional terms related to communication and expression

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation indicating the end of a textual segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urga
    -0.76
    atis
    -0.71
    ucci
    -0.68
    itone
    -0.66
    script
    -0.64
    isc
    -0.64
    paio
    -0.63
    rete
    -0.63
    manager
    -0.62
    patch
    -0.62
    POSITIVE LOGITS
     Known
    0.93
     Alive
    0.87
    entimes
    0.77
    selves
    0.72
    INGS
    0.71
     learnt
    0.71
     Seen
    0.70
    IER
    0.69
     Been
    0.68
     Wrong
    0.66
    Act Density 0.113%

    No Known Activations