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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that indicate something is well-known or widely recognized

    oai_token-act-pair · gpt-3.5-turbo

    the word "apparently" and its variations, indicating a focus on statements that suggest something is assumed or inferred rather than confirmed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.68
    allas
    -0.68
    lite
    -0.66
    west
    -0.65
    fc
    -0.64
    glas
    -0.62
    icipated
    -0.62
     Keane
    -0.61
    dden
    -0.61
    watch
    -0.61
    POSITIVE LOGITS
    icably
    0.87
     forgot
    0.70
     unrelated
    0.68
     insol
    0.67
     complied
    0.66
     conflic
    0.66
     plur
    0.65
     infring
    0.65
     contradict
    0.65
     endowed
    0.65
    Act Density 0.024%

    No Known Activations