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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political actions and governmental decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to political positions and changes in public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.58
    sylv
    -0.51
    estones
    -0.50
    emaker
    -0.49
    Unt
    -0.49
    ulla
    -0.48
    itus
    -0.48
    rack
    -0.47
    ocl
    -0.46
     challeng
    -0.45
    POSITIVE LOGITS
     namely
    0.79
     albeit
    0.78
     including
    0.74
     however
    0.71
     which
    0.70
     huh
    0.67
     though
    0.67
     although
    0.67
     according
    0.65
     meanwhile
    0.62
    Act Density 0.561%

    No Known Activations