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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different groups of people

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" in various contexts indicating connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.79
    GMT
    -0.76
    :(
    -0.72
    xt
    -0.68
    oret
    -0.64
    ONSORED
    -0.63
    going
    -0.61
    LOCK
    -0.60
    çķ
    -0.60
    :[
    -0.60
    POSITIVE LOGITS
    doms
    0.89
     assorted
    0.88
    gans
    0.81
     vice
    0.79
     other
    0.75
     consequently
    0.74
     alike
    0.74
     kindred
    0.71
     lifestyles
    0.69
     others
    0.68
    Act Density 0.320%

    No Known Activations