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

    Neuronpedia

    INDEX
    Explanations

    words related to names or titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ath" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reloaded
    -0.79
    ITED
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
     shorth
    -0.73
     Gemini
    -0.64
    ebus
    -0.64
    LOAD
    -0.64
    hift
    -0.64
     Petraeus
    -0.64
    enhagen
    -0.63
    POSITIVE LOGITS
    aniel
    1.07
    urst
    1.04
    ouse
    0.97
    reshold
    0.94
    lete
    0.90
    iop
    0.90
    omas
    0.89
    itect
    0.88
    alon
    0.88
    opter
    0.87
    Act Density 0.028%

    No Known Activations