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

    Neuronpedia

    INDEX
    Explanations

    words related to research, specifically highlighting phrases starting with "res"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rescue."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thing
    -0.76
     Cruiser
    -0.63
     flawed
    -0.61
     strings
    -0.60
     snippets
    -0.59
     Springs
    -0.59
     spo
    -0.59
     McAuliffe
    -0.59
     Germans
    -0.58
     Icelandic
    -0.57
    POSITIVE LOGITS
    olve
    1.49
    istance
    1.47
    olved
    1.45
    olutions
    1.44
    earcher
    1.39
    olving
    1.37
    idency
    1.37
    urrection
    1.36
    olver
    1.33
    ervation
    1.30
    Act Density 0.021%

    No Known Activations