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

    Neuronpedia

    INDEX
    Explanations

    references to personal growth and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÑĩÑĤобÑĭ
    -0.22
     aby
    -0.19
     Äijá»ĥ
    -0.19
     Ñīоб
    -0.19
    ·»
    -0.17
    ogr
    -0.16
    uyen
    -0.15
    819
    -0.15
    cwd
    -0.14
     nhằm
    -0.14
    POSITIVE LOGITS
    -to
    0.33
     todo
    0.28
     TO
    0.25
     tot
    0.24
    _to
    0.22
    -To
    0.21
    todo
    0.20
     tor
    0.20
     To
    0.20
     top
    0.20
    Act Density 0.142%

    No Known Activations