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

    Neuronpedia

    INDEX
    Explanations

    words following a specific word "Here" starting with a capital letter

    oai_token-act-pair · gpt-3.5-turbo

    the specific phrase "Here" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tongues
    -0.64
    omedical
    -0.60
    existent
    -0.59
    ONSORED
    -0.58
     acupuncture
    -0.58
    iour
    -0.56
    iven
    -0.55
     grace
    -0.55
    mong
    -0.54
    natureconservancy
    -0.54
    POSITIVE LOGITS
    tics
    1.19
    tical
    1.13
    abouts
    1.10
    tic
    1.04
    here
    0.89
    ford
    0.84
     Transcript
    0.83
    odore
    0.81
     Comes
    0.77
    htaking
    0.67
    Act Density 0.038%

    No Known Activations