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

    Neuronpedia

    INDEX
    Explanations

    instructional phrases relating to software installation and command execution

    oai_token-act-pair · gpt-3.5-turbo

    instructions or actions related to software installation and usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lasted
    -0.71
     Leilan
    -0.67
     absorbs
    -0.64
    ilts
    -0.61
     mourning
    -0.61
     overrun
    -0.61
    ergy
    -0.61
     ambul
    -0.60
    ĸļ
    -0.59
    ä¹ĭ
    -0.59
    POSITIVE LOGITS
    ername
    1.18
    Login
    1.02
     click
    0.97
     Login
    0.97
     login
    0.94
    Simply
    0.94
     clicks
    0.92
     clicking
    0.88
     Settings
    0.87
     CLICK
    0.87
    Act Density 0.490%

    No Known Activations