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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the beginning or start of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to beginnings or initial stages of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Stat
    -0.75
    Pitt
    -0.73
    Els
    -0.73
     SEN
    -0.71
    WA
    -0.70
    MON
    -0.69
    nesday
    -0.68
    >>\
    -0.66
    aples
    -0.66
    rosso
    -0.66
    POSITIVE LOGITS
     standpoint
    1.08
     perspective
    0.99
     onwards
    0.92
     perspectives
    0.77
     viewpoint
    0.76
    otype
    0.74
     vantage
    0.73
     onward
    0.67
     playbook
    0.66
    pter
    0.66
    Act Density 0.095%

    No Known Activations