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

    Neuronpedia

    INDEX
    Explanations

    statements expressing existence, state, or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦοÏį
    -0.16
    ahlen
    -0.15
    plusplus
    -0.13
    ови
    -0.13
     {{--<
    -0.12
    esine
    -0.12
    ãĤ¤ãĥĦ
    -0.11
     &);↵
    -0.11
    owy
    -0.11
     Destructor
    -0.11
    POSITIVE LOGITS
     fine
    0.20
     ok
    0.20
     OK
    0.19
    oko
    0.18
     kinda
    0.18
     okay
    0.17
     sufficient
    0.17
     deprecated
    0.17
     buggy
    0.16
     kosher
    0.16
    Act Density 0.241%

    No Known Activations