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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events involving people

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions involving death or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccess
    -0.67
    halla
    -0.65
    ety
    -0.60
    Versions
    -0.59
    proc
    -0.58
    omever
    -0.58
    renheit
    -0.58
     proc
    -0.58
     behav
    -0.57
    istani
    -0.56
    POSITIVE LOGITS
     Phant
    0.74
     LLP
    0.69
     Brewery
    0.67
     Xperia
    0.66
     Joined
    0.66
     Arsenal
    0.66
     Ashes
    0.65
     Bayern
    0.64
     Brewing
    0.63
     Rye
    0.61
    Act Density 0.523%

    No Known Activations