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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discovering or uncovering information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a desire to discover or learn information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.73
    interstitial
    -0.73
    atomic
    -0.70
    ortunately
    -0.70
    oples
    -0.70
    export
    -0.68
     oun
    -0.67
    ©¶æ
    -0.67
    ĪĴ
    -0.67
    oil
    -0.66
    POSITIVE LOGITS
    ledge
    0.83
    yer
    0.81
     how
    0.80
    wards
    0.79
    stadt
    0.78
    posts
    0.76
    izabeth
    0.70
     è£ıè
    0.68
    footed
    0.68
    bur
    0.67
    Act Density 0.027%

    No Known Activations