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

    Neuronpedia

    INDEX
    Explanations

    words that indicate personal opinions or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appropri
    -0.17
    _ipc
    -0.16
    rame
    -0.16
     нев
    -0.15
     Appropri
    -0.14
    ültür
    -0.14
    ASTER
    -0.14
    htable
    -0.14
    ame
    -0.14
    ehler
    -0.14
    POSITIVE LOGITS
     ax
    0.19
     obvious
    0.18
     observation
    0.18
     Consult
    0.17
     reasonable
    0.17
     observable
    0.17
     acknow
    0.17
     Universal
    0.16
    Observ
    0.16
     observ
    0.16
    Act Density 0.004%

    No Known Activations