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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific placeholder-like terms or unidentified entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.83
     uſed
    -0.81
     purpoſe
    -0.80
     Majefty
    -0.77
     myſelf
    -0.76
     ſtate
    -0.73
     whofe
    -0.73
     fince
    -0.72
    InjectAttribute
    -0.71
     Chriftian
    -0.71
    POSITIVE LOGITS
    !*\
    0.54
     OMITBAD
    0.54
    UnknownFieldSet
    0.54
    ADVERTISEMENT
    0.53
    ⊱
    0.51
    ={<
    0.50
     %@",
    0.48
    prisingly
    0.46
    ("}\
    0.46
    tvguidetime
    0.45
    Act Density 0.000%

    No Known Activations