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

    Neuronpedia

    INDEX
    Explanations

    verbs in the past tense relating to movement or existence towards a specific location or state

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthodox
    -0.75
    olor
    -0.69
    imon
    -0.69
    icons
    -0.69
    ruff
    -0.68
    tops
    -0.67
    shown
    -0.67
    icon
    -0.64
    ording
    -0.64
    stant
    -0.63
    POSITIVE LOGITS
     undone
    1.07
     forth
    0.96
     ashore
    0.89
     hither
    0.86
     closer
    0.80
     apart
    0.80
    leon
    0.79
     roaring
    0.77
     into
    0.77
     out
    0.76
    Act Density 0.504%

    No Known Activations