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

    Neuronpedia

    INDEX
    Explanations

    phrases comparing two things, stating that one thing is more like the other

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing comparisons or analogies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sharp
    -0.75
     Cros
    -0.70
     Vacc
    -0.69
    RAW
    -0.69
    ;;;;;;;;;;;;
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    ©¶æ¥µ
    -0.61
    Stars
    -0.60
    phia
    -0.60
    Arch
    -0.60
    POSITIVE LOGITS
     than
    1.53
    than
    1.48
     Than
    1.12
    erous
    0.77
    oult
    0.71
    cientious
    0.69
    rah
    0.68
    oot
    0.68
    vention
    0.67
    ner
    0.66
    Act Density 0.152%

    No Known Activations