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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "find" followed by various contexts and subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "find" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolet
    -0.79
    isoft
    -0.76
    brance
    -0.69
    apeake
    -0.68
    gap
    -0.65
    voy
    -0.63
    IQ
    -0.62
    externalActionCode
    -0.61
    eneg
    -0.61
    vous
    -0.60
    POSITIVE LOGITS
     yourself
    1.19
     themselves
    1.19
     ourselves
    1.16
     oneself
    1.16
     myself
    1.13
     herself
    1.12
     himself
    1.08
     yourselves
    1.08
     out
    1.08
     itself
    0.98
    Act Density 0.079%

    No Known Activations