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

    Neuronpedia

    INDEX
    Explanations

    words related to direction or descent

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of descending or falling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceous
    -0.59
    okemon
    -0.58
    isd
    -0.56
     avail
    -0.55
    ë
    -0.55
    INO
    -0.53
    archives
    -0.53
    ÙIJ
    -0.52
    ificent
    -0.52
    acity
    -0.51
    POSITIVE LOGITS
    grading
    1.23
    graded
    1.22
    LOAD
    1.11
    grades
    1.10
     stairs
    1.09
    stairs
    1.06
    river
    1.00
    hill
    0.95
    sized
    0.83
    wind
    0.82
    Act Density 0.066%

    No Known Activations