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

    Neuronpedia

    INDEX
    Explanations

    the word "very" with various strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    the word "very" and its frequent usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olor
    -0.77
    osal
    -0.75
    ensis
    -0.71
    igi
    -0.68
    adelphia
    -0.66
    onent
    -0.66
    iture
    -0.65
    ando
    -0.65
    onis
    -0.65
    zyk
    -0.63
    POSITIVE LOGITS
     seldom
    0.82
     similar
    0.81
     different
    0.81
     rarely
    0.81
     low
    0.79
     readable
    0.78
     rare
    0.78
     handy
    0.78
     informative
    0.77
     unlikely
    0.76
    Act Density 0.068%

    No Known Activations