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

    Neuronpedia

    INDEX
    Explanations

    log-in related actions and prompts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to logging into accounts or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.83
     gelatin
    -0.74
     focal
    -0.68
    OIL
    -0.65
    使
    -0.65
     tal
    -0.65
    ĸļ
    -0.64
    Grade
    -0.63
     gestation
    -0.62
     coating
    -0.61
    POSITIVE LOGITS
     Username
    0.76
    reens
    0.73
    ername
    0.72
    ministic
    0.70
     Register
    0.70
    ulhu
    0.70
    oshenko
    0.69
    anian
    0.69
    redit
    0.69
     subscrib
    0.68
    Act Density 0.063%

    No Known Activations