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

    Neuronpedia

    INDEX
    Explanations

    phrases related to definitions and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behalf
    -0.17
    gran
    -0.16
    eros
    -0.15
    acks
    -0.15
    aji
    -0.14
    ere
    -0.13
    ties
    -0.13
     repar
    -0.13
    531
    -0.13
     semiclass
    -0.13
    POSITIVE LOGITS
    Wunused
    0.18
    oeff
    0.16
    ussen
    0.15
    аÑĢÑħ
    0.15
    eated
    0.15
    developers
    0.14
    itto
    0.14
     abnormal
    0.14
     quay
    0.14
    endants
    0.14
    Act Density 0.041%

    No Known Activations