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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns that are objects of verbs

    oai_token-act-pair · gpt-3.5-turbo

    the word "whom" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roads
    -0.75
    pod
    -0.69
    âĨ
    -0.68
    ricks
    -0.66
    pad
    -0.66
    termin
    -0.64
    case
    -0.63
    reach
    -0.63
    Loading
    -0.63
    MG
    -0.63
    POSITIVE LOGITS
    soever
    1.92
     coh
    0.77
     dearly
    0.76
    irlf
    0.75
     whom
    0.74
    owship
    0.73
    awei
    0.71
     Allaah
    0.70
     superv
    0.69
    selves
    0.69
    Act Density 0.017%

    No Known Activations