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

    Neuronpedia

    INDEX
    Explanations

    combinations of letters at the beginning and end of words

    oai_token-act-pair · gpt-3.5-turbo

    mentions of communication and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.50
     dime
    -0.50
     referen
    -0.44
     thous
    -0.44
     Sunshine
    -0.44
    ãĥ¼ãĥĨ
    -0.42
     sovere
    -0.42
     Vaugh
    -0.41
     Instr
    -0.41
     helicop
    -0.40
    POSITIVE LOGITS
    NetMessage
    0.59
    xiety
    0.53
    lement
    0.53
    terness
    0.51
     largeDownload
    0.50
    anyahu
    0.49
    othe
    0.49
    tro
    0.48
    mosp
    0.48
    asm
    0.47
    Act Density 1.406%

    No Known Activations