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

    Neuronpedia

    INDEX
    Explanations

    phrases related to termination or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to termination or ending of contracts or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htaking
    -0.73
    iard
    -0.68
    tro
    -0.67
    artisan
    -0.67
    container
    -0.67
     Flavoring
    -0.65
    rouse
    -0.65
    NG
    -0.64
    gio
    -0.63
    ortment
    -0.63
    POSITIVE LOGITS
     termination
    0.94
     terminated
    0.82
    ials
    0.81
     terminate
    0.80
     termin
    0.79
    aneously
    0.76
    uates
    0.75
     abruptly
    0.75
    ities
    0.73
     prematurely
    0.73
    Act Density 0.017%

    No Known Activations