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

    Neuronpedia

    INDEX
    Explanations

    negative attributes or situations

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or terms related to fear or danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adjusted
    -0.86
     UD
    -0.83
     adequate
    -0.82
     terminated
    -0.81
     sufficient
    -0.80
     credible
    -0.79
     probable
    -0.77
     effective
    -0.77
     weighted
    -0.76
     strongly
    -0.76
    POSITIVE LOGITS
    loving
    1.58
    hun
    1.51
    watching
    1.50
    eating
    1.49
    turned
    1.49
    hunter
    1.45
    hunt
    1.44
    themed
    1.44
    machine
    1.42
    thing
    1.41
    Act Density 0.133%

    No Known Activations