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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "here" is mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gency
    -0.59
    ains
    -0.58
    idine
    -0.55
     WATCHED
    -0.55
    selage
    -0.54
    arov
    -0.54
    jar
    -0.53
    locking
    -0.53
    ãĥ»
    -0.52
    awar
    -0.52
    POSITIVE LOGITS
     here
    3.27
     HERE
    2.36
     Here
    1.87
     herein
    1.72
    here
    1.69
    Here
    1.53
     hither
    1.33
     hereafter
    1.16
     below
    1.13
     tonight
    1.09
    Act Density 0.052%

    No Known Activations