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

    Neuronpedia

    INDEX
    Explanations

    words related to particular approaches or methods

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating different approaches or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quished
    -0.79
    rings
    -0.78
     depended
    -0.73
    liga
    -0.73
    pool
    -0.72
    abytes
    -0.71
    horn
    -0.70
     belonged
    -0.66
    busters
    -0.66
    ather
    -0.64
    POSITIVE LOGITS
     dealing
    0.91
     achieving
    0.87
     resolving
    0.85
     selecting
    0.85
     combating
    0.84
     tackling
    0.83
     solving
    0.81
     discipline
    0.80
     interpreting
    0.77
     maximizing
    0.77
    Act Density 0.094%

    No Known Activations