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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long-standing situations or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to long-established concepts or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.85
    Stars
    -0.79
     teasp
    -0.73
    chat
    -0.72
    kay
    -0.70
    anamo
    -0.66
    EStream
    -0.66
    accompanied
    -0.66
    ËĪ
    -0.65
    oggles
    -0.65
    POSITIVE LOGITS
     favourite
    0.82
     collaborator
    0.77
     favorite
    0.76
     subsequ
    0.75
     relationship
    0.72
     staple
    0.71
     history
    0.69
    stay
    0.69
     acquaintance
    0.68
     profitable
    0.67
    Act Density 0.042%

    No Known Activations