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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unlimited access or resources

    oai_token-act-pair · gpt-3.5-turbo

    references to unlimited services or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquette
    -0.81
    geist
    -0.76
    bourg
    -0.72
    acus
    -0.69
    neys
    -0.69
    ective
    -0.68
    hran
    -0.67
    ochemical
    -0.66
    =-=-=-=-=-=-=-=-
    -0.66
    iger
    -0.66
    POSITIVE LOGITS
     access
    1.02
     amounts
    0.99
     amount
    0.86
     unlimited
    0.85
     quantities
    0.81
     remission
    0.73
     regress
    0.73
    itarian
    0.73
     bandwidth
    0.72
     privileges
    0.71
    Act Density 0.012%

    No Known Activations