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

    Neuronpedia

    INDEX
    Explanations

    words related to physical objects that can be stacked or grouped together

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transitions or changes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psychiatrists
    -0.72
     Canaver
    -0.72
     looph
    -0.70
    uploads
    -0.67
     Democr
    -0.60
     Belg
    -0.59
     Balk
    -0.58
     Sith
    -0.58
     Syri
    -0.57
     nihil
    -0.56
    POSITIVE LOGITS
    !.
    1.09
     safely
    0.99
    *.
    0.97
    +.
    0.93
    !".
    0.93
     :)
    0.91
    !
    0.90
     ðŁĻĤ
    0.88
     ASAP
    0.88
     :-)
    0.87
    Act Density 0.901%

    No Known Activations