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

    Neuronpedia

    INDEX
    Explanations

    the word "Whatever" or similar phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whatever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arie
    -0.85
    iard
    -0.79
    arb
    -0.75
    inently
    -0.75
    ea
    -0.74
    anamo
    -0.73
    aters
    -0.73
    azon
    -0.71
    arest
    -0.71
    olkien
    -0.70
    POSITIVE LOGITS
     happens
    1.30
     floats
    1.20
     else
    1.18
     happened
    1.14
    soever
    0.96
     transpired
    0.96
     arises
    0.89
     emerges
    0.84
     comes
    0.83
     awaits
    0.83
    Act Density 0.047%

    No Known Activations