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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters or attributes in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rib
    -0.19
     Äijô
    -0.16
    warz
    -0.15
    hek
    -0.15
    oir
    -0.15
    .ide
    -0.14
    åĸ
    -0.14
    esso
    -0.14
    iface
    -0.14
     Lesser
    -0.14
    POSITIVE LOGITS
     bet
    0.18
     Cory
    0.15
    614
    0.14
    amam
    0.14
    yme
    0.14
     Gür
    0.14
     spy
    0.14
     p
    0.14
    919
    0.14
     Hopkins
    0.13
    Act Density 0.001%

    No Known Activations