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

    Neuronpedia

    INDEX
    Explanations

    terms related to selection processes and criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ister
    -0.16
    ilden
    -0.15
    uito
    -0.15
    occo
    -0.15
    adaki
    -0.14
    centage
    -0.14
    neau
    -0.14
    cock
    -0.14
    ëħIJ
    -0.14
    lander
    -0.14
    POSITIVE LOGITS
    ivity
    0.38
    SingleNode
    0.26
    ive
    0.26
    ively
    0.24
     lá»įc
    0.24
    eted
    0.23
    IVITY
    0.23
    ivities
    0.22
    ted
    0.20
    ives
    0.19
    Act Density 0.056%

    No Known Activations