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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or evaluations about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yx
    -0.17
    jez
    -0.15
    rous
    -0.14
    AtA
    -0.14
    å®Ī
    -0.14
    ìĨIJ
    -0.13
     Jal
    -0.13
    ÛĮÚ©
    -0.13
    *))
    -0.13
    rai
    -0.13
    POSITIVE LOGITS
    udoku
    0.18
     aims
    0.16
    bower
    0.16
    aims
    0.16
     amac
    0.15
    odash
    0.15
    goal
    0.15
    goals
    0.15
     purposes
    0.15
     foremost
    0.15
    Act Density 0.193%

    No Known Activations