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

    Neuronpedia

    INDEX
    Explanations

    words related to motivation and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Companion
    -0.18
    chers
    -0.16
    omp
    -0.15
    egan
    -0.15
    lay
    -0.15
    ocular
    -0.15
    ural
    -0.15
    ieren
    -0.15
    ilder
    -0.15
    ppy
    -0.15
    POSITIVE LOGITS
    /prom
    0.22
     participation
    0.19
    /disable
    0.19
    /support
    0.18
    agement
    0.18
     Participation
    0.16
    ouver
    0.15
     us
    0.15
    umber
    0.15
     others
    0.15
    Act Density 0.029%

    No Known Activations