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

    Neuronpedia

    INDEX
    Explanations

    phrases spoken by official spokespersons or representatives

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespeople or representatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fertil
    -0.68
     convergence
    -0.64
     environmentalists
    -0.63
     snowball
    -0.62
    spir
    -0.61
    shape
    -0.58
     eco
    -0.57
     fixation
    -0.56
     jewels
    -0.56
     lumber
    -0.56
    POSITIVE LOGITS
     Brendan
    0.88
     Brian
    0.85
     Sgt
    0.83
     Sean
    0.81
     Steph
    0.80
     Dmitry
    0.79
     Capt
    0.79
    atoon
    0.77
     Lt
    0.77
     spokesman
    0.76
    Act Density 0.037%

    No Known Activations