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

    Neuronpedia

    INDEX
    Explanations

    expressions related to showing support or endorsement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hebdo
    -0.66
     pores
    -0.64
     darn
    -0.63
    vern
    -0.63
    ãĥ£
    -0.63
     carp
    -0.61
     Mile
    -0.61
     sweat
    -0.61
     nerve
    -0.61
     Nose
    -0.60
    POSITIVE LOGITS
    orship
    0.81
    bands
    0.81
    yip
    0.80
     Supports
    0.80
    Support
    0.79
     support
    0.76
    ament
    0.74
    rador
    0.73
    heses
    0.72
    ariat
    0.71
    Act Density 0.036%

    No Known Activations