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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of uncertainty or unclear connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     religieuses
    -0.63
    ówek
    -0.55
     dentelle
    -0.55
     kekasih
    -0.53
     cardiaque
    -0.52
     principalmente
    -0.52
     respectivement
    -0.52
     gracilis
    -0.51
     uyar
    -0.50
    lida
    -0.50
    POSITIVE LOGITS
    Somehow
    1.18
     Somehow
    1.13
     somehow
    1.07
    Somewhere
    0.92
     newBuilder
    0.86
     Somewhere
    0.84
     somewhere
    0.81
     magically
    0.76
    somewhere
    0.76
     inexp
    0.75
    Act Density 0.129%

    No Known Activations