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

    Neuronpedia

    INDEX
    Explanations

    phrases related to joining or supporting a cause or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the action of "jumping on" or participating in trends or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Policy
    -0.72
    pdf
    -0.69
    heastern
    -0.66
    isf
    -0.66
    minus
    -0.62
    lf
    -0.62
    larg
    -0.62
    ertodd
    -0.61
    respect
    -0.60
    ples
    -0.59
    POSITIVE LOGITS
     bandwagon
    1.01
     hoops
    0.90
    ulic
    0.76
     leaps
    0.74
     sidx
    0.72
    obin
    0.71
     wagon
    0.71
     conclusions
    0.69
    leon
    0.67
     straw
    0.64
    Act Density 0.132%

    No Known Activations