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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    references to reflective or analytical thoughts regarding societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.73
     PLUS
    -0.73
    EMA
    -0.72
    Marg
    -0.67
    Atl
    -0.65
    IRT
    -0.64
    ENE
    -0.63
    CHAT
    -0.63
    MT
    -0.63
     Rats
    -0.62
    POSITIVE LOGITS
     technically
    1.08
     ostensibly
    0.97
     initially
    0.80
     admittedly
    0.79
     theoretically
    0.78
     undeniably
    0.74
     somewhat
    0.73
     undoubtedly
    0.69
     occasional
    0.68
     pid
    0.67
    Act Density 0.407%

    No Known Activations