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

    Neuronpedia

    INDEX
    Explanations

    phrases related to clearing or making something disappear

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "clear" or "clearing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENTS
    -0.85
    Lenin
    -0.68
     nostalg
    -0.68
    egal
    -0.68
    ingo
    -0.66
    ties
    -0.66
    sson
    -0.65
    ENT
    -0.64
    ENCE
    -0.63
    iosity
    -0.61
    POSITIVE LOGITS
    houses
    0.97
     waivers
    0.93
    ewater
    0.91
    house
    0.88
    cut
    0.84
    ances
    0.83
    cuts
    0.82
    cast
    0.80
    cutting
    0.80
     skies
    0.79
    Act Density 0.049%

    No Known Activations