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

    Neuronpedia

    INDEX
    Explanations

    slashes or forward slashes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ese
    -0.19
    OV
    -0.14
    xit
    -0.14
    èĮĥ
    -0.14
    ÏĦαν
    -0.14
     Afterwards
    -0.14
     Mystery
    -0.13
    CUR
    -0.13
     branching
    -0.13
    illow
    -0.13
    POSITIVE LOGITS
    baugh
    0.19
    館
    0.16
    ceptar
    0.16
     modal
    0.15
    ucken
    0.15
    sher
    0.15
    .§
    0.15
    filer
    0.15
    ums
    0.14
    iores
    0.14
    Act Density 0.008%

    No Known Activations