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

    Neuronpedia

    INDEX
    Explanations

    phrases related to having something or accomplishing a task successfully

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.74
    è¦ļéĨĴ
    -0.66
    åħī
    -0.66
    2011
    -0.64
    displayText
    -0.63
    arry
    -0.62
    RESULTS
    -0.62
    SPONSORED
    -0.61
    Pokémon
    -0.61
     conduc
    -0.61
    POSITIVE LOGITS
     Talent
    0.95
    tin
    0.86
     precedence
    0.83
     rid
    0.83
    cha
    0.81
     plenty
    0.80
    ngth
    0.79
     Plenty
    0.77
    umen
    0.66
     been
    0.66
    Act Density 0.025%

    No Known Activations