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

    Neuronpedia

    INDEX
    Explanations

    instances of changes and modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Forward
    -0.15
     Fresh
    -0.15
    ells
    -0.15
    ith
    -0.14
    etsk
    -0.14
     bells
    -0.14
    .SH
    -0.14
    Ñľ
    -0.13
    adients
    -0.13
     Lal
    -0.13
    POSITIVE LOGITS
     into
    0.22
     Ø¥ÙĦÙī
    0.20
     to
    0.18
    ToOne
    0.17
    à¹Ģหล
    0.17
    åĪ°
    0.16
    èĩ³
    0.16
    PrototypeOf
    0.15
    ost
    0.15
    ocker
    0.15
    Act Density 0.149%

    No Known Activations