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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ending or stopping something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the termination of contracts or employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.90
    htaking
    -0.72
    izzy
    -0.69
    iard
    -0.67
    Edited
    -0.67
    artisan
    -0.66
    eller
    -0.66
    icket
    -0.64
    annis
    -0.64
    gio
    -0.63
    POSITIVE LOGITS
     termination
    1.18
     terminated
    1.03
     terminate
    0.93
     termin
    0.91
    uates
    0.82
     terminating
    0.79
     abruptly
    0.77
     warr
    0.73
     sever
    0.72
    angering
    0.71
    Act Density 0.007%

    No Known Activations