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

    Neuronpedia

    INDEX
    Explanations

    phrases related to challenging or difficult situations

    oai_token-act-pair · gpt-3.5-turbo

    references to "puppets" and "puppies."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.80
     willful
    -0.75
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
     dissolution
    -0.65
     logger
    -0.65
     corrosion
    -0.64
    APE
    -0.64
     Binding
    -0.64
     cort
    -0.63
    GW
    -0.62
    POSITIVE LOGITS
    sburgh
    1.23
    ortun
    1.18
    olicy
    1.16
    enthal
    1.14
    enhagen
    1.06
    etry
    0.99
    ete
    0.99
    onent
    0.98
    odcast
    0.98
    erman
    0.96
    Act Density 0.010%

    No Known Activations