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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or collective actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aryl
    -0.15
    igor
    -0.14
    kre
    -0.14
     ?><?
    -0.14
    gression
    -0.14
    Æ°Æ¡ng
    -0.14
    ignum
    -0.14
    ela
    -0.14
    ovie
    -0.13
    antha
    -0.13
    POSITIVE LOGITS
    ahn
    0.15
    entity
    0.14
    GI
    0.14
     strom
    0.14
    ander
    0.14
     collective
    0.14
    oly
    0.13
    Capabilities
    0.13
    aul
    0.13
    INST
    0.13
    Act Density 0.030%

    No Known Activations