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

    Neuronpedia

    INDEX
    Explanations

    terms related to modeling and computation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
     myſelf
    -0.52
     ſche
    -0.51
     ſtill
    -0.50
     didst
    -0.48
     AttributeSet
    -0.47
     srdce
    -0.44
     raiſ
    -0.44
     pleaſure
    -0.44
    FailureListener
    -0.44
    POSITIVE LOGITS
    uring
    0.54
     Plated
    0.52
     bezeichneter
    0.52
    URING
    0.49
    otyping
    0.47
     trending
    0.46
    tituting
    0.46
    ing
    0.45
    ặt
    0.44
    AGING
    0.44
    Act Density 0.686%

    No Known Activations