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

    Neuronpedia

    INDEX
    Explanations

    prompts to continue reading a story or article

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ranch
    -0.82
    otom
    -0.76
    rams
    -0.71
    ura
    -0.68
    ouls
    -0.68
    ramid
    -0.67
    istered
    -0.66
     bounty
    -0.66
     treat
    -0.65
     sucker
    -0.63
    POSITIVE LOGITS
     Continued
    1.07
     Continue
    1.06
    CLASSIFIED
    0.89
    ...]
    0.87
     Transcript
    0.81
    verett
    0.78
     convol
    0.76
     Loading
    0.75
    Reviewer
    0.75
     Advertisement
    0.74
    Act Density 0.009%

    No Known Activations