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

    Neuronpedia

    INDEX
    Explanations

    instances when something is made clear or obvious from a description or situation

    oai_token-act-pair · gpt-3.5-turbo

    the word "from" to indicate sources or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nets
    -0.72
    imes
    -0.72
    mouth
    -0.71
    bush
    -0.71
    isode
    -0.70
    idy
    -0.70
    illus
    -0.69
    icer
    -0.68
    icide
    -0.67
    busters
    -0.67
    POSITIVE LOGITS
     afar
    1.75
     whence
    1.15
     scratch
    1.04
     outset
    0.99
     thence
    0.95
     inside
    0.92
     standpoint
    0.92
     nowhere
    0.91
     within
    0.90
     elsewhere
    0.89
    Act Density 0.121%

    No Known Activations