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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the manner in which actions are performed

    oai_token-act-pair · gpt-3.5-turbo

    the word "manner" and its various contexts of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rament
    -0.75
    tek
    -0.73
    Dust
    -0.70
     Patri
    -0.69
     Hansen
    -0.65
    ammy
    -0.64
    oppable
    -0.64
     Wink
    -0.63
     Lyn
    -0.63
    hemat
    -0.63
    POSITIVE LOGITS
    isms
    1.24
    ality
    0.89
     dictated
    0.81
    othy
    0.78
    ism
    0.77
     largeDownload
    0.77
    istic
    0.76
     ACTIONS
    0.75
    able
    0.72
    abus
    0.71
    Act Density 0.019%

    No Known Activations