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

    Neuronpedia

    INDEX
    Explanations

    high-frequency phrases and complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fisher
    -0.16
     bro
    -0.16
     Emb
    -0.16
     tie
    -0.15
    dl
    -0.15
    aben
    -0.15
     ties
    -0.15
    Emb
    -0.15
     pres
    -0.14
    DD
    -0.14
    POSITIVE LOGITS
    beth
    0.15
    ATAL
    0.15
    _Cancel
    0.15
    javax
    0.15
    onta
    0.14
    igung
    0.14
     NÄĽm
    0.14
    alara
    0.14
    bé
    0.14
    beit
    0.14
    Act Density 0.005%

    No Known Activations