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

    Neuronpedia

    INDEX
    Explanations

    topics or subjects of discussion or conversation

    oai_token-act-pair · gpt-3.5-turbo

    references to discussions or conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     landfall
    -0.72
    aples
    -0.66
    undai
    -0.66
    Constructed
    -0.66
    anmar
    -0.65
     Soldier
    -0.65
    ascade
    -0.64
    served
    -0.64
    uilt
    -0.63
     handc
    -0.61
    POSITIVE LOGITS
    ership
    0.84
    bag
    0.77
     Talk
    0.77
    uces
    0.77
    bone
    0.76
    ucing
    0.75
     about
    0.75
    ers
    0.75
    ularity
    0.73
    ij士
    0.73
    Act Density 0.027%

    No Known Activations