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

    Neuronpedia

    INDEX
    Explanations

    phrases related to going out into different locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cens
    -0.81
    iasco
    -0.74
    interstitial
    -0.71
     Kund
    -0.64
    oqu
    -0.62
     Returning
    -0.61
    uman
    -0.59
    untarily
    -0.59
    downs
    -0.59
    erity
    -0.58
    POSITIVE LOGITS
     pasture
    1.06
     sea
    0.86
     countryside
    0.72
     loud
    0.67
     snipp
    0.67
    EMENT
    0.65
    tnc
    0.63
    Sea
    0.62
     creek
    0.62
     mole
    0.61
    Act Density 0.129%

    No Known Activations