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

    Neuronpedia

    INDEX
    Explanations

    sentences that involve conditional phrases or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    either
    -0.19
    empo
    -0.18
     Either
    -0.16
     entonces
    -0.16
    Either
    -0.15
     både
    -0.15
    ãĤĦ
    -0.15
     wiÄĻc
    -0.15
     EITHER
    -0.15
    gether
    -0.14
    POSITIVE LOGITS
     else
    0.55
    phans
    0.52
    ients
    0.48
    ifice
    0.43
     even
    0.42
     otherwise
    0.40
    acles
    0.39
    acular
    0.39
     worse
    0.38
    lando
    0.37
    Act Density 0.370%

    No Known Activations