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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discussions

    oai_token-act-pair · gpt-3.5-turbo

    conjectures or predictions about reactions to situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.63
     collaps
    -0.59
     destro
    -0.56
    roma
    -0.56
     canopy
    -0.54
     maintenance
    -0.53
     branching
    -0.53
     upkeep
    -0.53
     phys
    -0.52
     foliage
    -0.51
    POSITIVE LOGITS
     cynicism
    0.72
     disingen
    0.71
     rhet
    0.68
     rhetorical
    0.67
     hypocrisy
    0.62
     understatement
    0.60
     irony
    0.58
     Orwell
    0.57
    rael
    0.56
     hypocritical
    0.56
    Act Density 1.274%

    No Known Activations