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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causality or logic

    oai_token-act-pair · gpt-3.5-turbo

    propositions for establishing causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grunt
    -0.66
     bri
    -0.65
     Dungeons
    -0.61
     volleyball
    -0.61
    RPG
    -0.60
     bluff
    -0.59
    PF
    -0.58
    rolled
    -0.58
     bomber
    -0.58
     BT
    -0.58
    POSITIVE LOGITS
    forth
    0.82
    ilib
    0.77
    aucus
    0.75
    ablishment
    0.74
    ratulations
    0.71
    eming
    0.69
    xual
    0.67
    endant
    0.67
     disabling
    0.66
    ctors
    0.65
    Act Density 0.163%

    No Known Activations