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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific time or location events

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Around" followed by numerical details or time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.74
     tatt
    -0.67
    imm
    -0.67
     duct
    -0.66
     istg
    -0.64
     gard
    -0.61
    qua
    -0.60
     harb
    -0.59
    straight
    -0.59
    TF
    -0.59
    POSITIVE LOGITS
     Around
    0.85
    lihood
    0.85
    atform
    0.82
    abouts
    0.77
    iversal
    0.75
     Them
    0.71
    ength
    0.71
    £ı
    0.71
    Around
    0.71
    pread
    0.70
    Act Density 0.013%

    No Known Activations