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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discussions or solutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate proposals or plans for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flies
    -0.79
    iments
    -0.78
    ESPN
    -0.74
    words
    -0.72
    antry
    -0.72
    grounds
    -0.70
    advertisement
    -0.70
    casts
    -0.69
    mates
    -0.68
    encies
    -0.68
    POSITIVE LOGITS
     comprehensive
    1.14
     unified
    1.13
     boycott
    1.08
     gradual
    1.08
     solution
    1.01
     moratorium
    1.00
     balanced
    1.00
     permanent
    0.98
     showdown
    0.97
     reduction
    0.97
    Act Density 0.372%

    No Known Activations