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

    Neuronpedia

    INDEX
    Explanations

    terms related to collaboration and teaming up

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "collaboration" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leigh
    -0.76
     Sabha
    -0.74
    ¥µ
    -0.71
    thur
    -0.70
    atra
    -0.69
    phal
    -0.67
    gun
    -0.66
    ns
    -0.66
     Adin
    -0.65
    stal
    -0.65
    POSITIVE LOGITS
     collaborations
    1.00
     collaborators
    0.96
     collaborator
    0.91
     arrang
    0.89
     collaboration
    0.89
     collabor
    0.87
     partner
    0.87
    ivity
    0.85
     collaborating
    0.82
     partners
    0.80
    Act Density 0.029%

    No Known Activations