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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that end with a specific word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ended" alongside temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.96
    abee
    -0.77
    POST
    -0.74
    ustomed
    -0.74
    itness
    -0.72
    NBA
    -0.71
    FIELD
    -0.67
    itives
    -0.67
    caster
    -0.66
    ouble
    -0.65
    POSITIVE LOGITS
     bankruptcy
    0.81
    cember
    0.76
    hyde
    0.72
     apopt
    0.72
     ceremony
    0.69
     irreversible
    0.68
     TAMADRA
    0.67
     cliff
    0.66
     tragically
    0.66
    agos
    0.64
    Act Density 0.213%

    No Known Activations