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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "with" followed by a person or entity being interacted with or discussed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -1.01
    fighter
    -0.68
    uploads
    -0.67
    orius
    -0.65
    ischer
    -0.63
    chin
    -0.63
    price
    -0.62
    waters
    -0.62
    ynski
    -0.61
    killed
    -0.61
    POSITIVE LOGITS
     regards
    1.17
     regard
    1.14
     respect
    0.89
    stood
    0.85
     impunity
    0.81
    draw
    0.78
     representatives
    0.77
    =-=-=-=-
    0.74
     strangers
    0.71
     him
    0.68
    Act Density 0.078%

    No Known Activations