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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaboration and unity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize unity or togetherness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viol
    -0.77
     msec
    -0.63
    taker
    -0.62
    士
    -0.62
     nails
    -0.60
     Nightmares
    -0.59
    miss
    -0.58
     Blasio
    -0.58
    DERR
    -0.56
    mill
    -0.55
    POSITIVE LOGITS
     Together
    0.84
    together
    0.84
     dots
    0.78
     disparate
    0.78
     together
    0.76
     mutually
    0.73
     oppos
    0.72
    anyon
    0.71
     synergy
    0.71
     handshake
    0.71
    Act Density 0.414%

    No Known Activations