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

    Neuronpedia

    INDEX
    Explanations

    words related to 'trick'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the token "tr" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.73
     Cheong
    -0.69
    PR
    -0.67
    COM
    -0.64
    ez
    -0.64
     Grande
    -0.63
    SPA
    -0.62
    EXP
    -0.61
    PD
    -0.60
    PI
    -0.60
    POSITIVE LOGITS
    ayer
    0.91
    asonic
    0.86
    inity
    0.84
    terday
    0.81
    acement
    0.80
    acker
    0.80
    ODUCT
    0.80
    atically
    0.78
    istance
    0.77
    igion
    0.77
    Act Density 0.035%

    No Known Activations