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

    Neuronpedia

    INDEX
    Explanations

    mentions of discord or dissent

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "dissociation" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAYS
    -0.81
     Gat
    -0.74
    FORE
    -0.71
    çĦ
    -0.71
     stakes
    -0.68
    GER
    -0.67
     Werewolf
    -0.67
     Goff
    -0.65
     Archdemon
    -0.65
    THING
    -0.64
    POSITIVE LOGITS
    ociation
    1.30
    ident
    1.26
    ipation
    1.26
    oci
    1.23
    imilar
    1.22
    ociated
    1.20
    olving
    1.14
    ension
    1.13
    ertation
    1.09
    olute
    1.03
    Act Density 0.010%

    No Known Activations