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

    Neuronpedia

    INDEX
    Explanations

    the word "fresh" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "fresh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istine
    -0.68
    ylum
    -0.67
    Goal
    -0.63
    anity
    -0.63
    oried
    -0.62
     respecting
    -0.61
    rael
    -0.61
     incorrectly
    -0.60
    Ĥİ
    -0.59
    ques
    -0.58
    POSITIVE LOGITS
    ness
    1.23
    faced
    0.94
    lings
    0.91
    water
    0.88
    liness
    0.87
    lish
    0.85
     squeezed
    0.84
    waters
    0.84
    meat
    0.80
     breeze
    0.79
    Act Density 0.036%

    No Known Activations