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

    Neuronpedia

    INDEX
    Explanations

    terms related to group actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocrates
    -0.72
    xual
    -0.71
    jack
    -0.71
    regon
    -0.69
    ded
    -0.69
    gun
    -0.68
    close
    -0.67
    geon
    -0.67
    rentice
    -0.65
    ldon
    -0.65
    POSITIVE LOGITS
     collective
    1.03
     bargaining
    1.01
     endeavour
    0.81
    ãĤ¢ãĥ«
    0.79
     collectively
    0.78
    ãĤº
    0.77
     unconscious
    0.74
     effort
    0.73
     gasp
    0.72
    ãĥ¥
    0.71
    Act Density 0.005%

    No Known Activations