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

    Neuronpedia

    INDEX
    Explanations

    photo credits

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ļ½
    -0.76
    omore
    -0.70
    ibles
    -0.69
    stones
    -0.69
    houses
    -0.68
    etime
    -0.68
    iate
    -0.67
    bling
    -0.66
    amba
    -0.65
     hook
    -0.65
    POSITIVE LOGITS
     Actions
    0.75
    Constructed
    0.70
     ï
    0.69
     Caption
    0.69
    thumbnails
    0.69
     IMAGES
    0.68
    enes
    0.68
     PLoS
    0.68
     Panc
    0.67
     Vatican
    0.66
    Act Density 0.046%

    No Known Activations