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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreement, collaboration, and cooperation between entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mutual" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HOU
    -0.75
     Mandatory
    -0.73
    hner
    -0.72
    byss
    -0.72
    mins
    -0.71
    ————
    -0.70
    rb
    -0.70
    mble
    -0.70
    nox
    -0.69
    OPLE
    -0.69
    POSITIVE LOGITS
     acquaintance
    1.02
     admiration
    0.93
     agreement
    0.91
     understanding
    0.89
     masturbation
    0.89
     aid
    0.86
     mutual
    0.85
     acquaintances
    0.84
    izable
    0.82
     incomp
    0.80
    Act Density 0.042%

    No Known Activations