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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rsa
    -0.17
    paren
    -0.16
    deaux
    -0.15
    kel
    -0.15
    inch
    -0.15
    oster
    -0.15
    ivent
    -0.14
     offsetof
    -0.14
    /on
    -0.14
    ÃĶNG
    -0.14
    POSITIVE LOGITS
    ãģĿãĤĮãģ¯
    0.15
    bee
    0.14
     Äijó
    0.14
    either
    0.14
    upertino
    0.14
    iddy
    0.14
     either
    0.14
    ensch
    0.14
    TEL
    0.14
    whether
    0.14
    Act Density 0.027%

    No Known Activations