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

    Neuronpedia

    INDEX
    Explanations

    and emphasize future actions or expectations

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating future actions or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rollins
    -0.58
     Mn
    -0.57
     mattress
    -0.56
     Moss
    -0.55
     Walters
    -0.54
    amin
    -0.54
    umping
    -0.54
     blunt
    -0.54
    oulos
    -0.54
     Monaco
    -0.53
    POSITIVE LOGITS
     thereof
    0.86
    daq
    0.74
    sth
    0.72
     alike
    0.72
    uala
    0.71
    negie
    0.68
    ãĥ¼ãĥĨãĤ£
    0.67
    Ù
    0.67
    ql
    0.67
    ãĤ£
    0.65
    Act Density 0.361%

    No Known Activations