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

    Neuronpedia

    INDEX
    Explanations

    references to upcoming events or releases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umen
    -0.79
    var
    -0.70
    percent
    -0.69
    loop
    -0.69
    management
    -0.68
    rest
    -0.68
    oller
    -0.68
    activ
    -0.67
    anya
    -0.67
    requent
    -0.67
    POSITIVE LOGITS
    coming
    0.92
    ï¸
    0.83
     Masquerade
    0.83
     Sakuya
    0.80
     undone
    0.79
     Sorce
    0.79
     Comes
    0.77
     attractions
    0.75
     Showdown
    0.74
     Neigh
    0.74
    Act Density 0.006%

    No Known Activations