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

    Neuronpedia

    INDEX
    Explanations

    names and numerical values in sentences

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions and verbs related to actions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.84
     srfAttach
    -0.74
    daq
    -0.72
    ibaba
    -0.72
    orneys
    -0.70
    iferation
    -0.69
    itably
    -0.68
    Topics
    -0.68
    etheless
    -0.67
    naire
    -0.67
    POSITIVE LOGITS
     POV
    0.76
     Sawyer
    0.73
     Wash
    0.72
     Dek
    0.70
     Nose
    0.69
     Cabin
    0.69
     zip
    0.68
     Scot
    0.68
     Cobb
    0.67
     hawk
    0.66
    Act Density 0.432%

    No Known Activations