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

    Neuronpedia

    INDEX
    Explanations

    references to coins and their associated systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.88
    ConstraintMaker
    -0.81
    <unused41>
    -0.81
    [@BOS@]
    -0.80
    ſſung
    -0.80
    <unused14>
    -0.80
    <unused43>
    -0.80
    <pad>
    -0.80
    <unused74>
    -0.80
    <unused28>
    -0.79
    POSITIVE LOGITS
     safety
    0.48
    ono
    0.46
    ils
    0.42
    ,
    0.42
     Lenz
    0.42
    oro
    0.42
    ers
    0.41
    ids
    0.40
    ory
    0.40
    IG
    0.40
    Act Density 0.173%

    No Known Activations