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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email validation and error messages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email validation and account registration prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.77
    uay
    -0.65
    PK
    -0.60
    esm
    -0.60
    Keefe
    -0.59
    =-=-
    -0.57
    fml
    -0.57
    gom
    -0.57
    prim
    -0.55
    onz
    -0.54
    POSITIVE LOGITS
     herself
    0.61
     Cyrus
    0.52
    sylv
    0.52
     nurse
    0.52
    lain
    0.51
     unmarried
    0.51
     nurses
    0.50
     Cinnamon
    0.50
     childbirth
    0.48
    aina
    0.47
    Act Density 1.328%

    No Known Activations