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

    Neuronpedia

    INDEX
    Explanations

    words related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "found" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atever
    -0.72
     tert
    -0.67
    assisted
    -0.62
     paced
    -0.60
     fue
    -0.60
     nit
    -0.59
    cdn
    -0.58
    idium
    -0.58
    awk
    -0.56
    inducing
    -0.56
    POSITIVE LOGITS
    Ô
    0.81
    ĸļ
    0.80
    %%%%
    0.79
    mint
    0.77
    uments
    0.76
    ãĤ¼
    0.75
    omorphic
    0.74
    Ú
    0.74
    ãĤ¤ãĥĪ
    0.72
    dylib
    0.71
    Act Density 0.031%

    No Known Activations