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

    Neuronpedia

    INDEX
    Explanations

    phrases related to betrayal or treachery

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal matters and trials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensor
    -0.82
     Mechdragon
    -0.71
     Mellon
    -0.69
    ãģ®éŃĶ
    -0.68
    ENSE
    -0.68
    ensation
    -0.66
     Equity
    -0.65
    hyde
    -0.64
    Constructed
    -0.64
    ifference
    -0.62
    POSITIVE LOGITS
    pez
    1.00
    izoph
    0.86
    tro
    0.85
    ppings
    0.85
    warts
    0.84
    ph
    0.84
    fact
    0.84
     tra
    0.84
    tty
    0.82
    inen
    0.81
    Act Density 0.013%

    No Known Activations