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

    Neuronpedia

    INDEX
    Explanations

    quotes or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     �
    -0.66
    /)
    -0.64
    .)
    -0.63
    cum
    -0.62
     Âł Âł Âł Âł
    -0.61
     prompting
    -0.59
     ''
    -0.58
     (=
    -0.58
     listed
    -0.57
    ,)
    -0.56
    POSITIVE LOGITS
    withstanding
    1.01
    resa
    0.99
    %"
    0.94
    xiety
    0.93
    chieve
    0.90
    odore
    0.86
    "[
    0.86
    usterity
    0.86
    ntil
    0.84
    ircraft
    0.83
    Act Density 0.251%

    No Known Activations