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

    Neuronpedia

    INDEX
    Explanations

    contrasting statements or conditions

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "Yet" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tained
    -0.80
    tein
    -0.73
    ga
    -0.71
    omial
    -0.70
    rador
    -0.69
    atti
    -0.68
    edu
    -0.66
    packs
    -0.65
    machine
    -0.65
    ancial
    -0.65
    POSITIVE LOGITS
     somehow
    0.92
    tons
    0.86
     strangely
    0.82
     alas
    0.78
     despite
    0.77
    entimes
    0.75
     nonetheless
    0.73
     somew
    0.73
    oner
    0.72
     behold
    0.71
    Act Density 0.016%

    No Known Activations