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

    Neuronpedia

    INDEX
    Explanations

    words related to tasks or projects that require effort or collaboration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "work" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neum
    -0.77
     constitu
    -0.68
    antha
    -0.66
     Flavoring
    -0.63
     Ukrain
    -0.59
    ople
    -0.59
     Carey
    -0.58
     Gors
    -0.57
    cean
    -0.56
    IFIED
    -0.55
    POSITIVE LOGITS
     tirelessly
    0.95
    flows
    0.92
     towards
    0.91
     miracles
    0.91
     backwards
    0.91
    outs
    0.91
     wonders
    0.90
     overtime
    0.90
     harder
    0.89
     diligently
    0.87
    Act Density 0.071%

    No Known Activations