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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thoughts, actions, or feelings

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong visual or emotional states and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.79
    successfully
    -0.76
    inducing
    -0.76
    grave
    -0.75
    etheus
    -0.74
    afort
    -0.73
    egal
    -0.72
    olor
    -0.71
    tie
    -0.69
    robe
    -0.68
    POSITIVE LOGITS
     plain
    0.83
    ifiable
    0.81
     coincidence
    0.73
    cks
    0.70
     darn
    0.68
     Facts
    0.67
     curiosity
    0.67
     luck
    0.64
     scratch
    0.63
     shrug
    0.62
    Act Density 0.311%

    No Known Activations