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

    Neuronpedia

    INDEX
    Explanations

    references to equal opportunities or fairness in competitive situations

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions and activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iosis
    -0.81
    imaru
    -0.78
    lished
    -0.78
    ngth
    -0.76
    ifi
    -0.76
    IDA
    -0.76
    eva
    -0.76
    urdue
    -0.73
    ascript
    -0.73
    asus
    -0.73
    POSITIVE LOGITS
     mechanism
    0.91
     ability
    0.80
     agent
    0.79
     factor
    0.79
     circle
    0.78
     tendency
    0.74
    tons
    0.73
     assumption
    0.72
     force
    0.71
     spree
    0.71
    Act Density 0.315%

    No Known Activations