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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or states

    oai_token-act-pair · gpt-3.5-turbo

    words related to urgent issues and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amendment
    -0.51
     Kinnikuman
    -0.51
     pedigree
    -0.50
     Amendments
    -0.50
     bookstore
    -0.50
    Platform
    -0.49
     AV
    -0.49
     JPEG
    -0.48
    oute
    -0.48
     Handbook
    -0.47
    POSITIVE LOGITS
    ecause
    0.71
    ilaterally
    0.69
    \\\\\\\\\\\\\\\\
    0.66
    nesday
    0.65
    ogether
    0.64
    ONSORED
    0.63
    etheless
    0.63
    cember
    0.63
    selves
    0.60
    because
    0.59
    Act Density 0.951%

    No Known Activations