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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and admiration towards individuals for their support and positive influence

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and acknowledgement toward individuals who have positively influenced others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivably
    -0.84
    ptive
    -0.77
     guiActiveUn
    -0.76
    dict
    -0.75
    pmwiki
    -0.74
    '>
    -0.72
    odan
    -0.70
    umably
    -0.67
    uphem
    -0.67
    avorable
    -0.67
    POSITIVE LOGITS
     generations
    0.98
     countless
    0.88
     youth
    0.82
     professionalism
    0.81
     friendships
    0.79
     Scouting
    0.79
     community
    0.77
     Chic
    0.77
     grassroots
    0.74
     young
    0.74
    Act Density 0.544%

    No Known Activations