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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forming opinions or making judgments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to judgment and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gren
    -0.74
    icz
    -0.70
    adra
    -0.70
    corn
    -0.69
    Untitled
    -0.67
    lar
    -0.67
    sky
    -0.67
    blue
    -0.67
    eland
    -0.67
    algia
    -0.66
    POSITIVE LOGITS
     whether
    0.96
     objectively
    0.87
     assessing
    0.84
     criteria
    0.84
     harshly
    0.83
     severity
    0.83
     retrospect
    0.82
    itatively
    0.81
     probabilities
    0.80
     evaluating
    0.78
    Act Density 0.052%

    No Known Activations