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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical or legal actions and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Making
    -0.63
    æ©
    -0.63
    Clinton
    -0.62
    Jenn
    -0.61
    Reloaded
    -0.61
    Michigan
    -0.61
    Bloom
    -0.61
    Indiana
    -0.60
    spir
    -0.58
    Flash
    -0.58
    POSITIVE LOGITS
    ande
    0.87
    usalem
    0.75
     omn
    0.73
     los
    0.72
    ĸļ
    0.71
     este
    0.70
    untu
    0.70
    antam
    0.69
    rique
    0.69
     alle
    0.68
    Act Density 0.086%

    No Known Activations