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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and events happening in sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to events or situations that occur after a significant action or moment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inho
    -0.74
    ashtra
    -0.73
    quote
    -0.73
    QL
    -0.70
    IOR
    -0.68
    IUM
    -0.67
    LESS
    -0.66
    <?
    -0.65
    ãĥĺãĥ©
    -0.64
    ELY
    -0.63
    POSITIVE LOGITS
     arrival
    0.81
     initial
    0.77
     completion
    0.72
     revelation
    0.72
    noon
    0.71
     exhausting
    0.71
     unsuccessful
    0.71
     stal
    0.69
     expiration
    0.68
     incident
    0.68
    Act Density 0.251%

    No Known Activations