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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussions and institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of urgency or critical commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     herself
    -0.77
     lifes
    -0.76
     neighb
    -0.73
     wire
    -0.72
     Aval
    -0.69
     probation
    -0.69
     pipes
    -0.68
     alley
    -0.67
     negoti
    -0.67
     unaccount
    -0.67
    POSITIVE LOGITS
    Whether
    1.41
    Consider
    1.41
    Specifically
    1.40
    Firstly
    1.34
    While
    1.31
    Whereas
    1.31
    Unfortunately
    1.30
    Because
    1.30
    Since
    1.30
    Until
    1.29
    Act Density 0.673%

    No Known Activations