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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant consequences or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mente
    -2.27
     respectively
    -1.90
    matter
    -1.77
     etc
    -1.72
    ize
    -1.62
    age
    -1.51
    iverse
    -1.49
    noreply
    -1.48
    izes
    -1.45
    izer
    -1.43
    POSITIVE LOGITS
     burst
    1.63
     remarks
    1.62
     heap
    1.46
    cke
    1.45
    odem
    1.44
    posted
    1.43
     lay
    1.43
     conjecture
    1.43
    brahim
    1.43
    quire
    1.41
    Act Density 0.010%

    No Known Activations