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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clusions
    -0.16
    here
    -0.15
    enga
    -0.14
    warts
    -0.14
    anga
    -0.14
    erm
    -0.14
    è¿ĻéĩĮ
    -0.13
    -[
    -0.13
    lay
    -0.13
    ductive
    -0.13
    POSITIVE LOGITS
     statements
    0.25
     light
    0.23
     comments
    0.23
     remarks
    0.23
     wake
    0.21
     interviews
    0.21
     separate
    0.19
     letters
    0.19
     related
    0.18
     Tuesday
    0.17
    Act Density 0.092%

    No Known Activations