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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making processes and preferences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.56
    featureID
    -0.52
    ewe
    -0.50
     IOError
    -0.48
    ticity
    -0.47
     spalle
    -0.44
     tocado
    -0.44
     byte
    -0.43
     rangs
    -0.42
    ėl
    -0.42
    POSITIVE LOGITS
    protoimpl
    0.74
     Wicidata
    0.68
    ########.
    0.65
    UserScript
    0.62
     Normdatei
    0.59
    )_/¯
    0.58
    Enllaces
    0.56
    themselves
    0.56
    findpost
    0.56
    Fordítás
    0.55
    Act Density 0.052%

    No Known Activations