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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reactions or responses

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to emotional responses or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heses
    -0.77
    oln
    -0.76
    utical
    -0.72
    uum
    -0.72
    ourage
    -0.68
    prints
    -0.65
    cipl
    -0.64
    arc
    -0.64
    gdala
    -0.64
    ln
    -0.62
    POSITIVE LOGITS
     hearing
    1.08
     witnessing
    0.97
     seeing
    0.96
     sudden
    0.90
     suggestion
    0.86
     discovering
    0.85
     losing
    0.84
     impending
    0.81
     perceived
    0.81
     recalling
    0.80
    Act Density 0.808%

    No Known Activations