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

    Neuronpedia

    INDEX
    Explanations

    words related to discussions, negotiations, and formal dialogues

    oai_token-act-pair · gpt-3.5-turbo

    references to discussions and negotiations between parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ribution
    -0.71
    inion
    -0.71
    alach
    -0.70
    olls
    -0.70
    Sensor
    -0.67
    ardi
    -0.66
    Reader
    -0.65
    osate
    -0.65
    lesi
    -0.65
     Stores
    -0.63
    POSITIVE LOGITS
     involving
    0.93
    pace
    0.90
     negotiations
    0.88
     underway
    0.86
     commenced
    0.84
    hops
    0.84
     between
    0.82
     negotiators
    0.80
    hips
    0.80
    paces
    0.79
    Act Density 0.043%

    No Known Activations