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

    Neuronpedia

    INDEX
    Explanations

    quoted attributes or values in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.92
    ########.
    -0.90
    xase
    -0.84
     مشين
    -0.82
    LookAnd
    -0.73
     rtn
    -0.73
     dAtA
    -0.71
     NSCoder
    -0.71
     &___
    -0.70
    featureID
    -0.68
    POSITIVE LOGITS
    ="#"
    0.65
    )"
    0.60
    ?>"
    0.58
     Parr
    0.57
    }"
    0.57
    =""
    0.57
    klärt
    0.57
     }}"
    0.57
     bénéficient
    0.57
    )、
    0.55
    Act Density 0.080%

    No Known Activations