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

    Neuronpedia

    INDEX
    Explanations

    words related to specific languages, particularly "ese."

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific locations or geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azine
    -0.84
    ilater
    -0.82
    ihar
    -0.81
    razil
    -0.78
    alist
    -0.71
    ãĥ¼ãĥĨ
    -0.71
    rid
    -0.69
     Cumm
    -0.69
    iary
    -0.67
    ially
    -0.64
    POSITIVE LOGITS
    wei
    0.81
    clair
    0.78
    lect
    0.77
    heng
    0.75
    ktop
    0.75
    uth
    0.72
    y
    0.69
    zza
    0.68
     maj
    0.68
    vere
    0.68
    Act Density 0.028%

    No Known Activations