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

    Neuronpedia

    INDEX
    Explanations

    verbs related to change or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to change and its impact on reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     towed
    -0.62
    ortment
    -0.60
     maneu
    -0.60
     adapted
    -0.57
     experimented
    -0.56
    iblings
    -0.56
    asionally
    -0.56
    aries
    -0.55
     crept
    -0.55
     assorted
    -0.55
    POSITIVE LOGITS
     anymore
    1.40
     nor
    1.19
    nor
    1.06
     whatsoever
    0.99
     anything
    0.88
     slightest
    0.82
     anybody
    0.81
     any
    0.79
    SPONSORED
    0.77
    galitarian
    0.75
    Act Density 0.397%

    No Known Activations