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

    Neuronpedia

    INDEX
    Explanations

    advertisements

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisement-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meal
    -0.81
    quartered
    -0.75
    bred
    -0.72
     contingency
    -0.71
    »Ĵ
    -0.70
    venge
    -0.68
    borg
    -0.67
     martial
    -0.66
    ties
    -0.66
     clay
    -0.65
    POSITIVE LOGITS
     Advertisement
    1.11
     Thumbnails
    0.82
     @@
    0.80
    inson
    0.76
    vertising
    0.75
     Annotations
    0.72
     <!--
    0.72
    VERTISEMENT
    0.72
    ļéĨĴ
    0.71
    INGTON
    0.71
    Act Density 0.015%

    No Known Activations