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

    Neuronpedia

    INDEX
    Explanations

    words related to restrictions or limits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restrictions or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.85
    ools
    -0.70
    mone
    -0.68
    leader
    -0.67
    ashington
    -0.67
    eon
    -0.66
    ublic
    -0.66
    æ©
    -0.64
    cow
    -0.62
     Morrow
    -0.62
    POSITIVE LOGITS
     restraints
    0.86
     restricts
    0.83
    lessly
    0.76
     minded
    0.72
     constraints
    0.71
     liability
    0.71
     limiting
    0.71
     confinement
    0.70
     restricting
    0.69
    inous
    0.69
    Act Density 0.028%

    No Known Activations