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

    Neuronpedia

    INDEX
    Explanations

    words related to providing or receiving assistance or approval

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to backing or endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rim
    -0.68
     burg
    -0.62
    neys
    -0.62
    cha
    -0.61
    rey
    -0.60
    umin
    -0.60
     Nose
    -0.58
     vers
    -0.57
    ModLoader
    -0.57
     Hebdo
    -0.56
    POSITIVE LOGITS
    itism
    0.92
    Support
    0.80
    arity
    0.79
    ability
    0.77
    enance
    0.74
     Supports
    0.74
    byn
    0.72
    leader
    0.69
    roud
    0.69
    establishment
    0.69
    Act Density 0.062%

    No Known Activations