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

    Neuronpedia

    INDEX
    Explanations

    references to corporate executives or leaders

    oai_token-act-pair · gpt-3.5-turbo

    references to corporate executives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.72
    Temperature
    -0.68
    INGTON
    -0.67
    COMPLE
    -0.67
    ttp
    -0.67
    theless
    -0.65
    \/\/
    -0.64
    forth
    -0.63
    ength
    -0.63
     hitch
    -0.62
    POSITIVE LOGITS
     executives
    0.98
    doms
    0.80
     Doodle
    0.76
     exec
    0.75
    otonin
    0.71
     executive
    0.69
     overseeing
    0.68
    ority
    0.67
    porate
    0.67
    furt
    0.66
    Act Density 0.025%

    No Known Activations