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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods or strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases highlighting various methods or ways to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tis
    -0.74
    existent
    -0.72
    writ
    -0.71
    _.
    -0.70
    stars
    -0.69
    ominated
    -0.68
    doms
    -0.68
    osate
    -0.66
    dom
    -0.65
     dominates
    -0.63
    POSITIVE LOGITS
     remind
    1.18
     showcase
    1.10
     motivate
    1.07
     educate
    1.07
     highlight
    1.06
     reassure
    1.02
     morale
    1.00
     reminder
    0.99
     encourage
    0.97
     clarify
    0.97
    Act Density 0.433%

    No Known Activations