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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate time or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .joda
    -0.15
    à¸Ńà¸Ķ
    -0.14
    isp
    -0.14
    GameObject
    -0.13
    rastructure
    -0.13
    ochen
    -0.13
    itchens
    -0.13
    odel
    -0.13
    eni
    -0.13
    ÅĤad
    -0.13
    POSITIVE LOGITS
     leaving
    0.23
     joining
    0.22
     moving
    0.21
     Join
    0.20
     immigr
    0.20
     earning
    0.20
     becoming
    0.19
     leave
    0.19
     starting
    0.19
     assuming
    0.18
    Act Density 0.071%

    No Known Activations