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

    Neuronpedia

    INDEX
    Explanations

    words related to buildings and structures

    oai_token-act-pair · gpt-3.5-turbo

    specific single letters or short sequences that may denote particular significance in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.77
    MENTS
    -0.77
    kamp
    -0.71
    SHARE
    -0.71
     Reborn
    -0.70
    è£ħ
    -0.65
     Bots
    -0.64
    İĭ
    -0.63
    stadt
    -0.63
     Kills
    -0.62
    POSITIVE LOGITS
    ust
    0.92
    aund
    0.91
    arming
    0.91
    umped
    0.90
    asting
    0.87
    anc
    0.87
    aste
    0.86
    ake
    0.83
    asted
    0.83
    rest
    0.83
    Act Density 0.090%

    No Known Activations