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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of belonging or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ota
    -0.14
    ogen
    -0.14
    ve
    -0.14
    ÙĤÙĪÙĦ
    -0.14
    uper
    -0.14
    undi
    -0.14
     Hansen
    -0.13
     consort
    -0.13
    pon
    -0.13
     Sort
    -0.13
    POSITIVE LOGITS
     accomplishment
    0.15
    ovich
    0.15
     urgency
    0.15
    ahat
    0.14
    oss
    0.14
     entitlement
    0.14
    ãĥĭãĥ¥
    0.14
    actory
    0.13
     být
    0.13
     Gill
    0.13
    Act Density 0.025%

    No Known Activations