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

    Neuronpedia

    INDEX
    Explanations

    words related to things being detached or unattached

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of being unbound or disentangled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hispanic
    -0.71
     haste
    -0.70
    Americ
    -0.65
    Balt
    -0.60
     looted
    -0.59
    Council
    -0.57
    Mayor
    -0.55
    stadt
    -0.55
     Giuliani
    -0.54
     distressed
    -0.53
    POSITIVE LOGITS
    hered
    1.34
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.88
    vous
    0.86
    vironment
    0.83
    adoes
    0.82
    rake
    0.77
    uced
    0.75
    nesday
    0.75
    kinson
    0.73
    acles
    0.72
    Act Density 0.014%

    No Known Activations