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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions related to setting parameters or configurations

    oai_token-act-pair · gpt-3.5-turbo

    commands or instructions related to setting parameters and configurations in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.75
    sylvania
    -0.73
     Souls
    -0.71
    çī
    -0.68
    jamin
    -0.66
    059
    -0.65
    herty
    -0.65
    æѦ
    -0.65
     Deity
    -0.63
    ç«
    -0.63
    POSITIVE LOGITS
    tle
    0.94
    ters
    0.91
    ter
    0.91
    tering
    0.89
    Timeout
    0.88
    env
    0.87
     forth
    0.82
    TING
    0.78
    TOP
    0.75
    uid
    0.75
    Act Density 0.033%

    No Known Activations