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

    Neuronpedia

    INDEX
    Explanations

    the word "whatever"

    oai_token-act-pair · gpt-3.5-turbo

    the term "whatever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enberg
    -0.91
    ea
    -0.91
    ert
    -0.85
    enburg
    -0.84
    iard
    -0.82
    enthal
    -0.82
    agos
    -0.78
    por
    -0.78
    etr
    -0.78
    press
    -0.77
    POSITIVE LOGITS
     else
    1.13
    soever
    1.07
     happened
    1.03
     floats
    0.99
     happens
    0.99
     semblance
    0.86
     transpired
    0.85
    THING
    0.79
     happ
    0.74
     sorts
    0.74
    Act Density 0.022%

    No Known Activations